StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
Open accessThe DOI matches its Crossref record; 28 of the 30 references it cites were found in a registry or an index, and 2 are not checked yet.
Abstract
Computer graphics has experienced a recent surge of data-centric approaches for photorealistic and controllable content creation. StyleGAN in particular sets new standards for generative modeling regarding image quality and controllability. However, StyleGAN’s performance severely degrades on large unstructured datasets such as ImageNet. StyleGAN was designed for controllability; hence, prior works suspect its restrictive design to be unsuitable for diverse datasets. In contrast, we find the main limiting factor to be the current training strategy. Following the recently introduced Projected GAN paradigm, we leverage powerful neural network priors and a progressive growing strategy to successfully train the latest StyleGAN3 generator on ImageNet. Our final model, StyleGAN-XL, sets a new state-of-the-art on large-scale image synthesis and is the first to generate images at a resolution of 10242 at such a dataset scale. We demonstrate that this model can invert and edit images beyond the narrow domain of portraits or specific object classes. Code, models, and supplementary videos can be found at https://sites.google.com/view/stylegan-xl/ .
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“StyleGAN-XL overcomes the scalability issues of previous models, offering better sample diversity, generalization, and image fidelity.”
From Deepfake Media Forensics: Status and Future Challenges (2025) · cites this paper as [36]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Our hypothesis could explain the phenomenon that conditional generation is easier than unconditional (Mirza & Osindero, 2014;Liu et al., 2020;Sauer et al., 2022), as the data we condition on may have the same platonic structure as the data we are generating.”
From The Platonic Representation Hypothesis (2024) · cites this paper as Sauer et al., 2022
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“StyleGAN-XL [36] is an extension of the StyleGAN family, designed to generate high-quality images on diverse and unstructured datasets, particularly ImageNet.”
From Deepfake Media Forensics: Status and Future Challenges (2025) · cites this paper as [36]
The cited source says what the claim attributes to it.
In the citing paper
“The model achieves state-of-the-art performance in large-scale image synthesis, generating high-resolution images up to 1024 × 1024.”
From Deepfake Media Forensics: Status and Future Challenges (2025) · cites this paper as [36]
The cited source says what the claim attributes to it.
In the citing paper
“StyleGAN-XL incorporates Projected GAN training and a progressive growing strategy to enhance stability and scalability.”
From Deepfake Media Forensics: Status and Future Challenges (2025) · cites this paper as [36]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“However, when trained on large and unstructured datasets like ImageNet [Deng et al. 2009], StyleGANs do not achieve satisfactory results yet.”
MethodGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
The unreasonable effectiveness of deep features as a perceptual metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · arXiv · doi:10.48550/arxiv.1801.03924 · Cited by 24,812
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00068 · Cited by 14,623
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235 · cited 2×
“However, its architecture is more restrictive than a standard generator network [Karras et al. 2018; Radford et al. 2016] which seems to come at a price when training on complex”
BackgroundA Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714 · cited 7×
“Regularization improves results on uni-modal datasets like FFHQ [27] or LSUN [63], whereas it can be detrimental on multi-modal datasets [5, 19].”
BackgroundInfluentialProceedings of the 25th international conference on Machine learning - ICML '08
(2008) · doi:10.1145/1390156 · Cited by 6,680
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00813 · Cited by 6,332
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2019) · arXiv · doi:10.48550/arxiv.1912.04958 · Cited by 6,332
SwinIR: Image Restoration Using Swin Transformer
Liang, J., Cao, J., Sun, G., Zhang, K., Van Gool, L., & Timofte, R. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00210 · Cited by 4,734 · cited 2×
“the data with a super-resolution network [Liang et al. 2021], see supplementary.”
Method
Research works printed but not linked: 46
- Yuval Alaluf, Or Patashnik, Zongze Wu, Asif Zamir, Eli Shechtman, Dani Lischinski, and Daniel Cohen-Or. 2022. Third Time's the Charm? Image and Video Editing with StyleGAN3. arXiv.org abs/2201.13433 (2022). https://arxiv.org/abs/2201.13433 · arXiv
- Yuval Alaluf, Or Patashnik, and Daniel Cohen-Or. 2021. ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement. Proc. of the IEEE International Conf. on Computer Vision (ICCV) abs/2104.02699 (2021). https://arxiv.org/abs/2104.02699 · arXiv
- Andrew Brock, Jeff Donahue, and Karen Simonyan. 2019. Large Scale GAN Training for High Fidelity Natural Image Synthesis. In Proc. of the International Conf. on Learning Representations (ICLR) . OpenReview.net. https://openreview.net/forum? id=B1xsqj09Fm
- Arantxa Casanova, Marlène Careil, Jakob Verbeek, Michal Drozdzal, and Adriana Romero-Soriano. 2021. Instance-Conditioned GAN. In Advances in Neural Information Processing Systems (NeurIPS) .
- Lucy Chai, Jun-Yan Zhu, Eli Shechtman, Phillip Isola, and Richard Zhang. 2021. Ensembling With Deep Generative Views. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) . Computer Vision Foundation / IEEE, 1499715007. https://openaccess.thecvf.com/content/CVPR2021/html/Chai\_Ensembling\_ With\_Deep\_Generative\_Views\_CVPR\_2021\_paper.html momentum contrastive learning. arxiv.org:2003.04297
- Ting-Yun Chang and Chi-Jen Lu. 2020. TinyGAN: Distilling BigGAN for Conditional Image Generation. In Proc. of the Asian Conf. on Computer Vision (ACCV) (Lecture Notes in Computer Science, Vol. 12625) , Hiroshi Ishikawa, Cheng-Lin Liu, Tomás Pajdla, and Jianbo Shi (Eds.). 509-525. https://doi.org/10.1007/978-3-030-69538-5\_31 Xinlei Chen, Haoqi Fan, and Ross Girshick Kaiming He. 2020. Improved baselines with · DOI
- Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Proc. of the International Conf. on Learning Representations (ICLR) . OpenReview.net. https://openreview.net/ forum?id=YicbFdNTTy
- Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems (NeurIPS) ,
- Tom George Grigg, Dan Busbridge, Jason Ramapuram, and Russ Webb. 2021. Do Self-Supervised and Supervised Methods Learn Similar Visual Representations? arxiv.org:2110.00528
- Timofey Grigoryev, Andrey Voynov, and Artem Babenko. 2022. When, Why, and Which Pretrained GANs Are Useful?. In Proc. of the International Conf. on Learning Representations (ICLR) . https://openreview.net/forum?id=4Ycr8oeCoIh
- Gwern. 2020. Making Anime Faces with StyleGAN . Retrieved January 16, 2022 from https://www.gwern.net/Faces#stylegan2-ext-modifications/
- Erik Härkönen, Aaron Hertzmann, Jaakko Lehtinen, and Sylvain Paris. 2020. GANSpace: Discovering Interpretable GAN Controls. In Advances in Neural Information Processing Systems (NeurIPS) . https://proceedings.neurips.cc/paper/2020/hash/ 6fe43269967adbb64ec6149852b5cc3e-Abstract.html
- Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Advances in Neural Information Processing Systems (NeurIPS) . 6626-6637. https://proceedings.neurips.cc/paper/2017/hash/ 8a1d694707eb0fefe65871369074926d-Abstract.html
- Ali Jahanian, Lucy Chai, and Phillip Isola. 2020. On the "steerability" of generative adversarial networks. In Proc. of the International Conf. on Learning Representations (ICLR) . OpenReview.net. https://openreview.net/forum?id=HylsTT4FvB
- Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. 2018. Progressive Growing of GANs for Improved Quality, Stability, and Variation. In Proc. of the International Conf. on Learning Representations (ICLR) . OpenReview.net. https://openreview.net/ forum?id=Hk99zCeAb
- Tero Karras, Miika Aittala, Samuli Laine, Erik Härkönen, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2021. Alias-Free Generative Adversarial Networks. In Advances in Neural Information Processing Systems (NeurIPS) .
- Umut Kocasari, Alara Dirik, Mert Tiftikci, and Pinar Yanardag. 2022. StyleMC: MultiChannel Based Fast Text-Guided Image Generation and Manipulation. Proc. of the IEEE Winter Conference on Applications of Computer Vision (WACV) (2022). https: //arxiv.org/abs/2112.08493
- Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In Proc. of the International Conf. on Learning Representations (ICLR) .
- Daiqing Li, Huan Ling, Seung Wook Kim, Karsten Kreis, Adela Barriuso, Sanja Fidler, and Antonio Torralba. 2022. BigDatasetGAN: Synthesizing ImageNet with Pixelwise Annotations. arXiv.org (2022). https://arxiv.org/abs/2201.04684 · arXiv
- Huan Ling, Karsten Kreis, Daiqing Li, Seung Wook Kim, Antonio Torralba, and Sanja Fidler. 2021. EditGAN: High-Precision Semantic Image Editing. arXiv.org abs/2111.03186 (2021). https://arxiv.org/abs/2111.03186 · arXiv
- Bingchen Liu, Yizhe Zhu, Kunpeng Song, and Ahmed Elgammal. 2021. Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis. In Proc. of the International Conf. on Learning Representations (ICLR) . OpenReview.net. https: //openreview.net/forum?id=1Fqg133qRaI
- Lars M. Mescheder, Andreas Geiger, and Sebastian Nowozin. 2018. Which Training Methods for GANs do actually Converge?. In Proc. of the International Conf. on Machine learning (ICML) (Proceedings of Machine Learning Research, Vol. 80) . PMLR, 3478-3487. http://proceedings.mlr.press/v80/mescheder18a.html
- Takeru Miyato, Toshiki Kataoka, Masanori Koyama, and Yuichi Yoshida. 2018. Spectral Normalization for Generative Adversarial Networks. In Proc. of the International Conf. on Learning Representations (ICLR) . OpenReview.net. https://openreview.net/ forum?id=B1QRgziT-
- Alexander Quinn Nichol and Prafulla Dhariwal. 2021. Improved Denoising Diffusion Probabilistic Models. In Proc. of the International Conf. on Machine learning (ICML) (Proceedings of Machine Learning Research, Vol. 139) . PMLR, 8162-8171. http:// proceedings.mlr.press/v139/nichol21a.html
- Or Patashnik, Zongze Wu, Eli Shechtman, Daniel Cohen-Or, and Dani Lischinski. 2021. StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery. In Proc. of the IEEE International Conf. on Computer Vision (ICCV) . 2085-2094.
- Etienne Perot, Pierre de Tournemire, Davide Nitti, Jonathan Masci, and Amos Sironi. 2020. Learning to Detect Objects with a 1 Megapixel Event Camera. In Advances in Neural Information Processing Systems (NeurIPS) . https://proceedings.neurips.cc/ paper/2020/hash/c213877427b46fa96cff6c39e837ccee-Abstract.html
- Phillip Pope, Chen Zhu, Ahmed Abdelkader, Micah Goldblum, and Tom Goldstein. 2021. The Intrinsic Dimension of Images and Its Impact on Learning. In Proc. of the International Conf. on Learning Representations (ICLR) . OpenReview.net. https: //openreview.net/forum?id=XJk19XzGq2J
- Maithra Raghu, Thomas Unterthiner, Simon Kornblith, Chiyuan Zhang, and Alexey Dosovitskiy. 2021. Do Vision Transformers See Like Convolutional Neural Networks?. In Advances in Neural Information Processing Systems (NeurIPS) .
- Daniel Roich, Ron Mokady, Amit H. Bermano, and Daniel Cohen-Or. 2021. Pivotal Tuning for Latent-based Editing of Real Images. arXiv.org (2021). https://arxiv.org/ abs/2106.05744 · arXiv
- Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David J. Fleet, and Mohammad Norouzi. 2021. Image Super-Resolution via Iterative Refinement. arxiv.org:2104.07636
- Tim Salimans, Ian J. Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved Techniques for Training GANs. In Advances in Neural Information Processing Systems (NeurIPS) . 2226-2234. https://proceedings.neurips. cc/paper/2016/hash/8a3363abe792db2d8761d6403605aeb7-Abstract.html
- Axel Sauer, Kashyap Chitta, Jens Müller, and Andreas Geiger. 2021. Projected GANs Converge Faster. In Advances in Neural Information Processing Systems (NeurIPS) .
- Axel Sauer and Andreas Geiger. 2021. Counterfactual Generative Networks. In Proc. of the International Conf. on Learning Representations (ICLR) . OpenReview.net. https: //openreview.net/forum?id=BXewfAYMmJw
- Yujun Shen and Bolei Zhou. 2021. Closed-Form Factorization of Latent Semantics in GANs. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) . 1532-1540. https://openaccess.thecvf.com/content/CVPR2021/html/Shen\_Closed-Form\_Factorization\_of\_Latent\_Semantics\_in\_GANs\_CVPR\_2021\_paper.html
- Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In Proc. of the International Conf. on Learning Representations (ICLR) . https: //openreview.net/forum?id=St1giarCHLP
- Nurit Spingarn, Ron Banner, and Tomer Michaeli. 2021. GAN "Steerability" without optimization. In Proc. of the International Conf. on Learning Representations (ICLR) . OpenReview.net. https://openreview.net/forum?id=zDy\_nQCXiIj
- Mingxing Tan and Quoc V. Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In Proc. of the International Conf. on Machine learning (ICML) (Proceedings of Machine Learning Research, Vol. 97) , Kamalika Chaudhuri and
- Matthew Tancik, Pratul P. Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T. Barron, and Ren Ng. 2020. Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains. In Advances in Neural Information Processing Systems (NeurIPS) . https://proceedings.neurips.cc/paper/2020/hash/ 55053683268957697aa39fba6f231c68-Abstract.html
- Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Hervé Jégou. 2021. Training data-efficient image transformers & distillation through attention. In Proc. of the International Conf. on Machine learning (ICML) (Proceedings of Machine Learning Research, Vol. 139) . PMLR, 10347-10357. http://proceedings.mlr.press/v139/touvron21a.html
- Aäron van den Oord, Oriol Vinyals, and Koray Kavukcuoglu. 2017. Neural Discrete Representation Learning. In Advances in Neural Information Processing Systems (NeurIPS) , Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 6306-6315. https://proceedings. neurips.cc/paper/2017/hash/7a98af17e63a0ac09ce2e96d03992fbc-Abstract.html
- Daniel Watson, Jonathan Ho, Mohammad Norouzi, and William Chan. 2021. Learning to Efficiently Sample from Diffusion Probabilistic Models. CoRR abs/2106.03802 (2021). https://arxiv.org/abs/2106.03802 · arXiv
- Andrey Voynov and Artem Babenko. 2020. Unsupervised Discovery of Interpretable Directions in the GAN Latent Space. In Proc. of the International Conf. on Machine learning (ICML) . PMLR, 9786-9796. http://proceedings.mlr.press/v119/voynov20a. html
- Zongze Wu, Dani Lischinski, and Eli Shechtman. 2021. StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) . Computer Vision Foundation / IEEE, 12863-12872. https://openaccess.thecvf.com/content/CVPR2021/html/Wu\_ StyleSpace\_Analysis\_Disentangled\_Controls\_for\_StyleGAN\_Image\_Generation\_ CVPR\_2021\_paper.html
- Rui Xu, Xintao Wang, Kai Chen, Bolei Zhou, and Chen Change Loy. 2021. Positional Encoding As Spatial Inductive Bias in GANs. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) . Computer Vision Foundation / IEEE, 1356913578. https://openaccess.thecvf.com/content/CVPR2021/html/Xu\_Positional\_ Encoding\_As\_Spatial\_Inductive\_Bias\_in\_GANs\_CVPR\_2021\_paper.html
- Fisher Yu, Yinda Zhang, Shuran Song, Ari Seff, and Jianxiong Xiao. 2015. LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop. arxiv.org:1506.03365
- Shengyu Zhao, Zhijian Liu, Ji Lin, Jun-Yan Zhu, and Song Han. 2020. Differentiable Augmentation for Data-Efficient GAN Training. In Advances in Neural Information Processing Systems (NeurIPS) . https://proceedings.neurips.cc/paper/2020/hash/ 55479c55ebd1efd3ff125f1337100388-Abstract.html
Cited by
Items 201–300 of 793
DiffuMatting: Synthesizing Arbitrary Objects with Matting-Level Annotation
Hu, X., Xu, P., Luo, D., Ji, X., Peng, J., Jiang, Z., Zhang, J., Jin, T., Wang, C., & Ji, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73113-6_23 · Cited by 24
Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models
Li, Y., Zhang, Y., Liu, S., & Lin, X. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888554 · Cited by 28
“Diffusion models [1]–[3], [33] are proposed to capture the high-dimensional nature of data distributions, which are dominating a new era by exceeding the Generative adversarial networks (GANs) [34], [35].”
Ko, H.-K., An, S., Park, G., Kim, S. K., Kim, D., Kim, B., Jo, J., & Seo, J. (2022) · Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3526113.3545612 · Cited by 23
“To support this, we could try using a recent model, InsetGAN [30], which generates a full body of characters.”
Methodvan Dreven, J., Cheddad, A., Alawadi, S., Ghazi, A. N., Koussa, J. A., & Vanhoudt, D. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110662 · Cited by 23
Maturana, C. N. V., Orozco, A. L. S., & Villalba, L. J. G. (2023) · Applied Sciences · doi:10.3390/app131910637 · Cited by 24
You Don’t Have to Be Perfect to Be Amazing: Unveil the Utility of Synthetic Images
Xing, X., Felder, F., Yang, N., Papanastasiou, G., Walsh, S. L. F., & Yang, G. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43904-9_2 · Cited by 23
Visions of Destruction: Exploring a Potential of Generative AI in Interactive Art
Solà, M. C., & Guljajeva, V. (2024) · International Symposium on Visual Information Communication and Interaction (VINCI) · doi:10.1145/3678698.3687185 · Cited by 23
Ni, Y., & Koniusz, P. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00646 · Cited by 23
“GANs, known for their rapid generation speeds [82] and high-fidelity image synthesis [81], have become go-to tools for applications such as text-to-image generation [35, 82, 94], image-to-image translation [45, 73, 76, 87], video synthesis [86, 103, 110] and 3D generation [92, 114, 124].”
TexOct: Generating Textures of 3D Models with Octree-based Diffusion
Liu, J., Wu, C., Liu, X., Liu, X., Wu, J., Peng, H., Zhao, C. X., Feng, H., Liu, J., & Ding, E. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00410 · Cited by 23
“This method effectively links 3D texture generation with 2D image generation techniques, such as GAN [13, 18, 31, 35, 46] and Diffusion models [10, 27, 29, 30].”
MethodSAN: Inducing Metrizability of GAN with Discriminative Normalized Linear LayerPreprint
Takida, Y., Imaizumi, M., Shibuya, T., Lai, C.-H., Uesaka, T., Murata, N., & Mitsufuji, Y. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2301.12811 · Cited by 23
“Lastly, we apply our SAN training framework to StyleGAN-XL (Sauer et al., 2022), which is a state-of-the-art GAN-based generative model.”
BackgroundMethodInfluentialPasarkar, A. P., & Dieng, A. B. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.12952 · Cited by 23
DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete LatentsPreprint
Xu, Y., Corso, G., Jaakkola, T., Vahdat, A., & Kreis, K. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.03300 · Cited by 23
“…et al., 2022) 1.23 1000 DisCo-Diff ( ours ; w/ Restart (Xu et al., 2023a)) 1.22 623 class-conditioned, w/ adversarial objective IC-GAN (Casanova et al., 2021) 6.70 1 BigGAN-deep (Brock et al., 2018) 4.06 1 CTM (Kim et al., 2023a) 1.92 1 StyleGAN-XL (Sauer et al., 2022) 1.51 1 structure of the data.”
InfluentialCustomize Your Visual Autoregressive Recipe with Set Autoregressive ModelingPreprint
Liu, W., Zhuo, L., Xin, Y., Xia, S., Gao, P., & Yue, X. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.10511 · Cited by 23
Zheng, K., Chen, Y., Chen, H., He, G., Liu, M., Zhu, J., & Zhang, Q. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.01103 · Cited by 25
SpectralAR: Spectral Autoregressive Visual Generation
Huang, Y., Chen, W., Zheng, W., Duan, Y., Zhou, J., & Lu, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01470 · Cited by 22
ForamViT-GAN: Exploring New Paradigms in Deep Learning for Micropaleontological Image Analysis
Ferreira, I., & Koeshidayatullah, A. (2023) · IEEE Access · doi:10.1109/access.2023.3291620 · Cited by 22
“the-art implementation for image generation tasks [33], [36].”
BackgroundMethodHow to Boost Face Recognition with StyleGAN?
Sevastopolsky, A., Malkov, Y. A., Durasov, N., Verdoliva, L., & Nießner, M. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01913 · Cited by 21
“Finally, various architectures typically used for self-supervised learning (such as transformers or highly scalable generative models [45]), might allow for the construction of more flexible methods due to heterogeneous inputs and outputs.”
TVG: A Training-Free Transition Video Generation Method With Diffusion Models
Zhang, R., Chen, Y., Liu, Y., Wang, W., Wen, X., & Wang, H. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3547337 · Cited by 21
Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising
Bemana, M., Leimkühler, T., Myszkowski, K., Seidel, H., & Ritschel, T. (2025) · Computer Graphics Forum · doi:10.1111/cgf.70086 · Cited by 22
ProtoGAN: Towards high diversity and fidelity image synthesis under limited data
Yang, M., Wang, Z., Chi, Z., & Du, W. (2023) · Information Sciences · doi:10.1016/j.ins.2023.03.042 · Cited by 21
Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows
Vérine, A., Négrevergne, B., Pydi, M. S., & Chevaleyre, Y. (2023) · neural information processing systems · doi:10.52202/075280-1413 · Cited by 21
A Geometric Perspective on Diffusion ModelsPreprint
Chen, D., Zhou, Z., Mei, J.-P., Shen, C., Chen, C., & Wang, C. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.19947 · Cited by 21
“This sort of training-free approaches improve the synthesis quality almost for free, but their NFEs (≥10) are still too large compared to GANs (Karras et al., 2020; Sauer et al., 2022).”
BackgroundHierarchical painter: Chinese landscape painting restoration with fine-grained styles
Xu, Z., Shang, H., Yang, S., Xu, R., Yan, Y., Li, Y., Huang, J., Yang, H. C., & Zhou, J. (2023) · Visual Intelligence · doi:10.1007/s44267-023-00021-y · Cited by 20
“StyleGAN-XL [41] utilizes super-resolution [42] and stemleaf staged training [13] that can produce meticulous images up to 1024 × 1024 resolution.”
MethodAssessing the Capacity of a Denoising Diffusion Probabilistic Model to Reproduce Spatial Context
Deshpande, R., Özbey, M., Li, H., Anastasio, M. A., & Brooks, F. J. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3414931 · Cited by 20
“These included two popular diffusion models: Denoising Diffusion Probabilistic Model (DDPM) [20] and MedFusion [21] a kind of a latent diffusion model (LDM), and two popular GAN architectures: StyleGAN2 (SG2) [15] and StyleGAN-XL (SG-XL) [48].”
MethodResultNitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training
Chen, D.-Y., Bandyopadhyay, H., Zou, K., & Song, Y.-Z. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00717 · Cited by 20
“StyleGAN-XL [42] and StyleGAN-T [43] use multiple discriminator heads alongside a frozen, pre-trained backbone, enabling feedback across feature pyramids to capture various levels of detail.”
Feng, B. Y., Xie, M., & Metzler, C. A. (2022) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2023.3234225 · Cited by 20
“For the IN condition, we use the weights of StyleGAN-XL [5] pretrained on the ImageNet dataset [40].”
BackgroundMethodInfluentialPTW: Pivotal Tuning Watermarking for Pre-Trained Image GeneratorsPreprint
Lukas, N., & Kerschbaum, F. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.07361 · Cited by 20
“We experiment with three StyleGAN-based architectures: StyleGAN2 [26], StyleGAN3 [25] and StyleGAN-XL [44].”
BackgroundMethodRevisiting Latent Space of GAN Inversion for Robust Real Image Editing
Katsumata, K., Vo, D. M., Liu, B., & Nakayama, H. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00523 · Cited by 20
“In addition to 2D GANs [15, 32, 33], GAN inversion has also been investigated for the recently developed 3D GANs [1,4,6,8,10,21,24,37,38,40,48,50].”
BackgroundFPGAN-Control: A Controllable Fingerprint Generator for Training with Synthetic Data
Shoshan, A., Bhonker, N., Ben-Baruch, E., Nizan, O., Kviatkovsky, I., Engelsma, J. J., Aggarwal, M., & Medioni, G. G. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00596 · Cited by 19
“First, the state-of-the-art tools for photo-realistic image generation have seen a significant leap in terms of image quality [11, 23, 24, 34, 37] and the level of control over the generated output [10,27,38,40].”
BackgroundDado, T., Papale, P., Lozano, A., Le, L., Wang, F., van Gerven, M. A. J., Roelfsema, P. R., Güçlütürk, Y., & Güçlü, U. (2024) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1012058 · Cited by 19
Khorram, S., Jiang, M., Shahbazi, M., Danesh, M. H., & Li, F. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00724 · Cited by 19
“In the past few years, research on Generative Adversarial Networks (GANs) [7] has led to remarkable advances in generating realistic images [2, 17, 41].”
BackgroundMethodInfluentialControllable image synthesis methods, applications and challenges: a comprehensive survey
Huang, S., Li, Q., Liao, J., Wang, S., Liu, L., & Li, L. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10987-w · Cited by 19
Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction
Hu, T., Zhang, J., Yi, R., Weng, J., Wang, Y., Zeng, X., Xue, Z., & Ma, L. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00873 · Cited by 19
“We compare our model with the GAN-based methods [5, 25, 40], diffusion-based meth-ods [13, 21, 34, 38], mask-prediction-based methods [7] and autoregressive-based methods [14, 29, 41, 47] on ImageNet [11].”
Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis
Zhu, J., Yang, C., Zheng, K., Xu, Y., Shi, Z., Zhang, Y., Chen, Q., & Shen, Y. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01716 · Cited by 19
“Following prior arts [7, 34, 37, 38, 71, 72], we adopt FID [27] as the metric, which evaluates a generator at the distribution level.”
InfluentialImproving 3D-Aware Image Synthesis with a Geometry-Aware Discriminator
Shi, Z., Xu, Y., Shen, Y., Zhao, D., Chen, Q., & Yeung, D. (2022) · neural information processing systems · doi:10.52202/068431-0575 · Cited by 19
clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIPPreprint
Pinkney, J. N. M., & Li, C. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.02347 · Cited by 19
“Throughout this work we have chosen the StyleGAN family of architectures due to the wide range of pre-trained models available[28] and its high-resolution, fast inference and state of the art performance in many domains[14, 35].”
MethodExact Diffusion Inversion via Bi-directional Integration ApproximationPreprint
Zhang, G., Lewis, J. P., & Kleijn, W. B. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.10829 · Cited by 19
“In comparison to generative adversarial networks (GANs) [9; 1; 10; 29],”
BackgroundDiffusion Models Are Innate One-Step GeneratorsPreprint
Zheng, B., & Yang, T. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.20750 · Cited by 20
FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion ModelPreprint
Wang, Z., Lu, Z., Huang, D., Zhou, C., Yue, X., Ouyang, W., & Bai, A. L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.13925 · Cited by 19
“We show samples from the FiTv2 in Fig 1, and we compare against some state-of-the-art class-conditional generative models: BigGAN [49], StyleGAN-XL [50], MaskGIT [51], CDM [52], Large-DiT [41], MaskDiT [43], Efficient-DiT [53], SimpleDiffusion [54], Flag-DiT [41], U-ViT [25], ADM [6], LDM [5], MDT…”
Exploring Precision and Recall to assess the quality and diversity of LLMsPreprint
Bronnec, F. L., Vérine, A., Négrevergne, B., Chevaleyre, Y., & Allauzen, A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.10693 · Cited by 19
“Numbers and images are from Kynkäänniemi et al. (2019). tion becomes necessary to enable a deeper and more precise understanding of generative models, as illustrated by the simple example of Figure 2.”
Spiking generative adversarial network with attention scoring decoding
Feng, L., Zhao, D., & Zeng, Y. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106423 · Cited by 18
Unveiling Differences in Generative Models: A Scalable Differential Clustering Approach
Zhang, J., Jalali, M., Li, C. T., & Farnia, F. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00774 · Cited by 18
“We tested generative models following standard frameworks, including GAN-based BigGAN [6], GigaGAN [22], StyleGAN-XL [41], InsGen [47], diffusion-based LDM [38], DiT-XL [32], and VAE-based RQ-Transformer [26], VDVAE [7].”
Content-based Search for Deep Generative Models
Lu, D., Wang, S.-Y., Kumari, N., Agarwal, R., Tang, M., Bau, D., & Zhu, J.-Y. (2023) · SIGGRAPH Asia Conference Papers · doi:10.1145/3610548.3618189 · Cited by 18
“…including GANs [Gal et al. 2022b; Karras et al. 2018, 2021, 2020b; Kumari et al. 2022; lucid layers 2022; Mokady et al. 2022; Pinkney 2020; Sauer et al. 2022; Wang et al. 2021, 2022], diffusion models [Dhariwal and Nichol 2021; Ho et al. 2020; Ruiz et al. 2022; Song et al. 2021a],…”
BackgroundFake It Till You Make It: Towards Accurate Near-Distribution Novelty DetectionPreprint
Mirzaei, H., Salehi, M., Shahabi, S., Gavves, E., Snoek, C. G. M., Sabokrou, M., & Rohban, M. H. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.14297 · Cited by 18
“[23] Axel Sauer, Katja Schwarz, and Andreas Geiger.”
BackgroundMethodInfluentialTsai, C.-T., Ko, C.-Y., Chung, I., Wang, Y.-C. F., & Chen, P. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.19117 · Cited by 18
SD3.5-Flash: Distribution-Guided Distillation of Generative Flows
Bandyopadhyay, H., Entezari, R., Scott, J., Adithyan, R., Song, Y.-Z., & Jampani, V. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37419-6_7 · Cited by 17
GI-SMN: Gradient Inversion Attack Against Federated Learning Without Prior Knowledge
Qian, J., Wei, K., Wu, Y., Zhang, J., Chen, J., & Bao, H. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5603-2_36 · Cited by 17
ACT-Diffusion: Efficient Adversarial Consistency Training for One-Step Diffusion Models
Kong, F., Duan, J., Sun, L., Cheng, H., Xu, R., Shen, H. T., Zhu, X., Shi, X., & Xu, K. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00849 · Cited by 17
Peer Is Your Pillar: A Data-Unbalanced Conditional GANs for Few-Shot Image Generation
Li, Z., Wang, C., Rui, X., Xue, C., Leng, J., Fu, Z., & Li, B. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3485109 · Cited by 17
Progress in Medical AI: Reviewing Large Language Models and Multimodal Systems for Diagnosis
Tong, R., Xu, T., Ju, X., & Wang, L. (2025) · AI Med · doi:10.71423/aimed.20250105 · Cited by 17
“Style-GAN also uses progressive growth[102], where the generator and discriminator initially handle low-resolution images during early training.”
Autoregressive Distillation of Diffusion Transformers
Kim, Y., Anagnostidis, S., Du, Y., Schönfeld, E., Köhler, J., Georgopoulos, M., Pumarola, A., Thabet, A., & Sanakoyeu, A. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01468 · Cited by 19
Neural Residual Diffusion Models for Deep Scalable Vision Generation
Ma, Z., Zhao, L., Qi, B., & Zhou, B. (2024) · neural information processing systems · doi:10.52202/079017-3729 · Cited by 17
Bridging CLIP and StyleGAN through Latent Alignment for Image EditingPreprint
Zheng, W., Li, Q., Guo, X., Wan, P., & Wang, Z. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.04506 · Cited by 17
“Besides, we have also integrated our method on Style-GAN3 [17] and StyleGAN-XL [34] for experiments on animal face dataset AFHQ [6, 7] and ImageNet [10].”
Private GANs, RevisitedPreprint
Bie, A., Kamath, G., & Zhang, G. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.02936 · Cited by 17
“Recent work scaling up StyleGAN to diverse datasets – StyleGAN-XL (Sauer et al., 2022) and GigaGAN (Kang et al.”
BackgroundTerDiT: Ternary Diffusion Models with TransformersPreprint
Lu, X., Zhou, A., Lin, Z., Liu, Q., Xu, Y., Zhang, R., Yang, X., Yan, J., Gao, P., & Li, H. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.14854 · Cited by 17
MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image GenerationPreprint
Chen, W., Niu, L., Lu, Z., Meng, F., & Zhou, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.19937 · Cited by 17
“In recent years, the field of generative image models in computer vision has witnessed significant advancements, particularly in class-to-image (Gao et al. (2023); Sun et al. (2024); Sauer et al. (2022)) and text-to-image tasks (Yu et al. (2022; 2023); Bao et al. (2023)).”
BackgroundDistilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow MatchingPreprint
Liu, E., Ning, X., Wang, Y., & Lin, Z. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.17153 · Cited by 17
Targeted Deep Learning System Boundary Testing
Weißl, O., Abdellatif, A., Chen, X., Merabishvili, G., Riccio, V., Kacianka, S., & Stocco, A. (2026) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3771557 · Cited by 16
“StyleGAN [23, 24, 26, 50] extends the GAN architecture to introduce new methods for controlling the image synthesis process.”
InfluentialELT: Elastic Looped Transformers for Visual Generation
Goyal, S., Agrawal, S., Anil, G. G., Jain, P., Paul, S., & Kusupati, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37324-3_17 · Cited by 18
Stylized Face Sketch Extraction via Generative Prior with Limited Data
Yun, K., Seo, K., Seo, C. W., Yoon, S., Kim, S., Ji, S. K., Ashtari, A., & Noh, J. (2024) · Computer Graphics Forum · doi:10.1111/cgf.15045 · Cited by 16
“Among various realistic face image generation methods [SSG22, HBB22, LZG ∗ 21, WZH ∗ 22, KLA ∗ 20b, KAH ∗ 20b], we utilized StyleGAN2 with the weights pretrained by the FFHQ [KLA19] dataset to generate high quality face images.”
Method3D Priors-Guided Diffusion for Blind Face Restoration
Lu, X., Hu, X., Luo, J., Zhu, B., Ruan, Y., & Ren, W. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681611 · Cited by 16
Accelerating Image Generation with Sub-path Linear Approximation Model
Xu, C., Song, T., Feng, W., Li, X., Ge, T., Zheng, B., & Wang, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73668-1_19 · Cited by 16
Park, D., Lee, S., Kim, S., Lee, S., Hong, Y., & Kim, H. (2024) · neural information processing systems · doi:10.52202/079017-2859 · Cited by 16
Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models
Yoon, S., Hwang, H., Kwon, D., Noh, Y., & Park, F. C. (2024) · neural information processing systems · doi:10.52202/079017-0776 · Cited by 17
Hallucinating Pose-Compatible Scenes
Brooks, T., & Efros, A. A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19787-1_29 · Cited by 16
USIS: Unsupervised Semantic Image Synthesis
Eskandar, G., Abdelsamad, M., Armanious, K., & Yang, B. (2023) · Computers & Graphics · doi:10.1016/j.cag.2022.12.010 · Cited by 16
Revisiting the Evaluation of Image Synthesis with GANs
Yang, M., Yang, C., Zhang, Y., Bai, Q., Shen, Y., & Dai, B. (2023) · neural information processing systems · doi:10.52202/075280-0417 · Cited by 16
High Fidelity Image Synthesis With Deep VAEs In Latent SpacePreprint
Luhman, T., & Luhman, E. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.13714 · Cited by 16
“All numbers taken from Dhariwal & Nichol (2021) except for LDM and StyleGAN-XL, which we take from their corresponding papers.”
MethodInfluentialEffective and Efficient Masked Image Generation ModelsPreprint
You, Z., Ou, J., Zhang, X., Hu, J., Zhou, J., & Li, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.07197 · Cited by 16
“Modern visual generation models primarily fall into four categories: GANs (Goodfellow et al., 2014; Brock, 2018; Sauer et al., 2022), diffusion models (Song et al., 2020; Sohl-Dickstein et al., 2015; Ho et al., 2020), masked prediction models (Chang et al., 2022; Li et al., 2023; 2024), and…”
Tooth Development Prediction Using a Generative Machine Learning Approach
Kokomoto, K., Okawa, R., Nakano, K., & Nozaki, K. (2024) · IEEE Access · doi:10.1109/access.2024.3416748 · Cited by 15
“For our image-generation model, we utilized StyleGAN-XL [22], an enhanced version 87646 VOLUME 12, 2024 Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
MethodResultGlobal Counterfactual Directions
Sobieski, B., & Biecek, P. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73036-8_5 · Cited by 15
Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction
Wang, Y., Bai, W., Zhang, C., Zhang, D., Luo, W., & Sun, H. (2025) · neural information processing systems · doi:10.52202/085713-1914 · Cited by 15
High-Fidelity Functional Ultrasound Reconstruction via a Visual Auto-Regressive Framework
Chen, X., Li, Z., Shen, Y., Mahmud, M., Pham, H., Ng, M. K.-P., Pun, C., & Wang, S. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3623196 · Cited by 15
Denoising Token Prediction in Masked Autoregressive Models
Yao, T., Li, Y., Pan, Y., Qiu, Z., & Mei, T. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01675 · Cited by 15
How to train your pre-trained GAN models
Park, S.-W., Kim, J.-Y., Park, J., Jung, S.-H., & Sim, C.-B. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04807-x · Cited by 15
Diversity-Aware Channel Pruning for StyleGAN Compression
Chung, J., Hyun, S., Shim, S.-H., & Heo, J. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00755 · Cited by 15
“Thanks to recent progress in generative artificial intelligence, there have been numerous techniques in the research field of image generation [2, 4, 12, 17, 20, 29, 33, 34, 36, 39].”
BackgroundAn Interpretable Evaluation of Entropy-based Novelty of Generative ModelsPreprint
Zhang, J., Li, C. T., & Farnia, F. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.17287 · Cited by 15
KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion ModelsPreprint
Navard, P., Monsefi, A. K., Zhou, M., Chao, W., Yılmaz, A., & Ramnath, R. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.01595 · Cited by 15
“Recent advances in DM have enabled high-quality image generation with improved sample diversity [4, 10, 11, 14, 23, 26, 28, 29, 35, 38, 42], often exceeding the performance of Generative Adversarial Networks (GAN) [7, 15, 16, 40].”
Goyal, H., Wajid, M. S., Wajid, M. A., Khanday, A. M. U. D., Neshat, M., & Gandomi, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.01029 · Cited by 15
Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling
Lee, K., Yu, S., & Shin, J. (2025) · International Conference on Learning Representations · doi:10.48550/arxiv.2510.24474 · Cited by 15
“…al., 2023; Bao et al., 2023; Hatamizadeh et al., 2024; Peebles & Xie, 2023; Ma et al., 2024; Yu et al., 2025; Karras et al., 2024b), and various generative models such as GANs (Sauer et al., 2022), Normalizing Flows (Gu et al., 2025), and autoregressive models (Tian et al., 2024; Li et al., 2024).”
BIGVSAN: Enhancing Gan-Based Neural Vocoders with Slicing Adversarial Network
Shibuya, T., Takida, Y., & Mitsufuji, Y. (2024) · ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp48485.2024.10446121 · Cited by 14
“GAN was first applied to image generation [23], and various GANs have achieved impressive results in not only image generation [27, 28] but also vocoding tasks.”
MethodIdentify Backdoored Model in Federated Learning via Individual Unlearning
Xu, J., Zhang, Z., & Hu, R. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00773 · Cited by 14
A Review Toward Deep Learning for High Dynamic Range Reconstruction
Martins, G. D. L., Lopez-Cabrejos, J., Martins, J., Leher, Q. O., Ferreti, G. D. S., Carvalho, L. H. C., Lima, F. B., Paixão, T., & Alvarez, A. B. (2025) · Applied Sciences · doi:10.3390/app15105339 · Cited by 14
CIPS-3D++: End-to-End Real-Time High-Resolution 3D-Aware GANs for GAN Inversion and Stylization
Zhou, P., Xie, L., Ni, B., & Tian, Q. C. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3285648 · Cited by 14
Pinetz, T., Kobler, E., Haase, R., Deike‐Hofmann, K., Radbruch, A., & Effland, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43895-0_57 · Cited by 14
Text to Image Generation and Editing: A SurveyPreprint
Yang, P., Ma, X., & Cheung, N. M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5704145 · Cited by 14
SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational AutoencoderPreprint
Shi, M., Wang, H., Zhang, B., Zheng, W., Zeng, B., Yuan, Z., Wu, X., Zhang, Y., Yang, H., Wang, X., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.11749 · Cited by 14
“…et al., 2014; Arjovsky et al., 2017; Gulrajani et al., 2017; Karras et al., 2019; Zhu et al., 2017; Radford et al., 2016; Karras et al., 2018; Sauer et al., 2022) generate high-fidelity images via adversarial training but often suffer unstable training, model collapse, and poor…”
SoFlow: Solution Flow Models for One-Step Generative ModelingPreprint
Luo, T., Yuan, H., & Liu, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.15657 · Cited by 14
Report on the AAPM grand challenge on deep generative modeling for learning medical image statistics
Deshpande, R., Kelkar, V. A., Gotsis, D. S., Prabhat, K. C., Zeng, R., Myers, K. J., Brooks, F. J., & Anastasio, M. A. (2024) · Medical Physics · doi:10.1002/mp.17473 · Cited by 13
Rethinking data imbalance in class incremental surgical instrument segmentation
Zhao, S., Bai, L., Yuan, K., Li, F., Yu, J., Dong, W., Wang, G., Islam, M., Padoy, N., Navab, N., et al. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103728 · Cited by 14
“Our SurgCSS framework includes the class-aware blending with inpainting to generate a class-balanced dataset by separating instrument foregrounds from surgical”
Generative adversarial networks: A comprehensive survey
Al-Yaari, A., & Deng, Y. (2026) · Systems and Soft Computing · doi:10.1016/j.sasc.2026.200460 · Cited by 13
Dual adversarial attacks: Fooling humans and classifiers
Schneider, J., & Apruzzese, G. (2023) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2023.103502 · Cited by 13
Householder Projector for Unsupervised Latent Semantics Discovery
Song, Y., Zhang, J., Sebe, N., & Wang, W. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00709 · Cited by 13
“In the past few years, GAN-based generative models [15] have achieved remarkable progress in high-fidelity image synthesis [43, 24, 5, 27, 28, 26, 25, 39, 6, 16, 50, 46].”
BackgroundImagiNet: A Multi-Content Benchmark for Synthetic Image DetectionPreprint
Boychev, D., & Cholakov, R. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.20020 · Cited by 13
Diffusion Models Need Visual Priors for Image GenerationPreprint
Yue, X., Wang, Z., Lu, Z., Sun, S., Wei, M., Ouyang, W., Bai, L., & Zhou, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.08531 · Cited by 13
“Diffusion models have surpassed previous state-of-the-art generative frameworks, such as GANs (Sauer et al., 2022; Goodfellow et al., 2014; 2020) and VAEs (Kingma & Welling, 2013), offering superior sample quality, improved training stability, and enhanced scalability.”
Adversarial Flow ModelsPreprint
Lin, S., Yang, C., Lin, Z., Chen, H., & Fan, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.22475 · Cited by 13
“Unlike [21, 23], we do not consider StyleGAN-XL [73] trained on ImageNet fits the data leakage description.”
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
Sun, P., Jiang, Y., Chen, S., Zhang, S., Peng, B., Luo, P., & Yuan, Z. (2024) · arXiv · doi:10.48550/arxiv.2406.06525 · Cited by 12
“In Table 6, we compare with popular image generation models, including GAN [Brock et al. 2018; Kang et al. 2023; Sauer et al. 2022], Diffusion models [Dhariwal & Nichol 2021; Ho et al. 2022b; Rombach et al. 2022; Peebles & Xie 2023], and masked-prediction models [Chang et al. 2022].”
MethodA High-Quality GAN With Data Augmentation for Aircraft Skin Defect Detection Under Limited Data
Li, H., Wang, C., & Liu, Y. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3420361 · Cited by 12
“With the development of GANs, a series of models such as StyleGAN3, StyleGAN-XL, and Projected-GAN [22], [23], [24] have been proposed.”
MethodWho did it? How User Agency is influenced by Visual Properties of Generated Images
Didion, J. K., Wolski, K., Wittchen, D., Coyle, D., Leimkühler, T., & Strohmeier, P. (2024) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3654777.3676335 · Cited by 12
Liu, J., Wu, J., Gao, X., Hu, J., Xiong, B., Liu, X., Zhao, C., Pei, H., Feng, H., Li, Y., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02474 · Cited by 13
“Despite substantial advancements in 2D image synthesis and 3D shape generation using GANs [40, 42] and diffusion models [12, 38, 39], achieving high-quality garment texture generation remains challenging.”
Metadata
- Authors
- Sauer, A., Schwarz, K., & Geiger, A.
- Affiliations
- Max Planck Institute for Intelligent Systems (DE)
- Venue
- Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings
- Publisher
- ACM
- Published
- 2022-08-07
- Pages
- 1-10
- OpenAlex
- W4285981784
- Cited by
- 353
- References
- 19
- Citations by year
- 2026: 42 · 2025: 84 · 2024: 122 · 2023: 86 · 2022: 19
- FWCI
- 28.20
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM SIGGRAPH Conference (SIGGRAPH) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
- Keywords
- StyleGAN3, StyleGAN, ImageNet, image inversion, image editing, high-resolution image generation, generative adversarial networks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.