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 101–200 of 793
Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
Teng, J., Zheng, W., Ding, M., Hong, W., Wangni, J., Yang, Z., & Tang, J. (2023) · International Conference on Learning Representations · doi:10.48550/arxiv.2309.03350 · Cited by 79
He, Y., Li, S., Li, K., Wang, J., Li, B., Shi, T., Xin, Y., Li, K., Yin, J., Zhang, M., et al. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129649 · Cited by 77
Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
Sauer, A., Boesel, F., Dockhorn, T., Blattmann, A., Esser, P., & Rombach, R. (2024) · arXiv · doi:10.48550/arxiv.2403.12015 · Cited by 76
“[Sauer et al. 2023a, 2022].”
Self-citationLearning Robust Deep Visual Representations from EEG Brain Recordings
Singh, P., Dalal, D., Vashishtha, G., Miyapuram, K. P., & Raman, S. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00738 · Cited by 75
“In recent years, image synthesis with GAN has reached the limit of photorealistic images, which is indistinguishable from real images [18, 35].”
BackgroundFreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models
Kang, B., Xu, X., Kang, B., Shi, Y., & Zhao, H. (2023) · neural information processing systems · doi:10.52202/075280-0819 · Cited by 73
SinDDM: A Single Image Denoising Diffusion ModelPreprint
Kulikov, V., Yadin, S., Kleiner, M., & Michaeli, T. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.16582 · Cited by 72
“State-of-the art generative models now reach high levels of photo-realism (Sauer et al., 2022; Ho et al., 2020; Dhariwal & Nichol, 2021), can treat arbitrary image dimensions (Chai et al., 2022), can be used to solve a variety of image restoration and manipulation tasks (Saharia et al., 2022c;a;…”
BackgroundZhang, J., Liu, Y., Yang, H., & Cao, 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/cvpr52733.2024.01151 · Cited by 68
“2, we show an example of the StyleGAN-XL [48] employed in our FedKTL.”
InfluentialIs Artificial Intelligence Generated Image Detection a Solved Problem?
Li, Z., Yan, J., He, Z., Zeng, K., Jiang, W., Xiong, L., & Fu, Z. (2025) · neural information processing systems · doi:10.52202/085713-5739 · Cited by 70
Deep generative models for detector signature simulation: A taxonomic review
Hashemi, H., & Krause, C. (2024) · Reviews in Physics · doi:10.1016/j.revip.2024.100092 · Cited by 66
“It requires a significant amount of patience and hyperparameter tuning for domain-specific tasks, but when it generalizes well, it can produce remarkably high-resolution samples [58, 59] with high fidelity.”
BackgroundDimensions underlying the representational alignment of deep neural networks with humans
Mahner, F. P., Muttenthaler, L., Güçlü, U., & Hebart, M. N. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01041-7 · Cited by 70
“…targeting a single DNN unit or a cluster of units, our approach aimed to selectively Article https://doi.org/10.1038/s42256-025-01041-7 amplify activation in dimensions of the DNN embedding across the entire DNN layer, using a pretrained generative adversarial neural network (StyleGAN-XL 58 ).”
InfluentialFasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification
Yao, J., Wang, C., Liu, W., & Wang, X. (2024) · neural information processing systems · doi:10.52202/079017-1787 · Cited by 67
Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion ModelsPreprint
Fei, Z., Fan, M., Yu, C., Li, D., & Huang, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.04478 · Cited by 66
Scaling Text-to-Image Diffusion Transformers with Representation AutoencodersPreprint
Tong, S., Zheng, B., Wang, Z., Tang, B., Ma, N., Brown, E., Yang, J., Fergus, R., LeCun, Y., & Xie, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.16208 · Cited by 66
“Following RAE, we adopt ℓ 1 , LPIPS [99], and adversarial losses [33, 68].”
MagicTime: Time-Lapse Video Generation Models as Metamorphic Simulators
Yuan, S., Huang, J., Shi, Y., Xu, Y., Zhu, R., Lin, B., Cheng, X., Yuan, L., & Luo, J. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3558507 · Cited by 64
“Compared to variational autoencoders (VAEs) [12, 13], flow-based models [14, 15], and generative adversarial networks (GANs) [16, 17, 18], diffusion models [19, 20, 21, 22, 23, 24] have demonstrated exceptional efficacy in image modeling.”
One-Step Diffusion Distillation via Deep Equilibrium Models
Geng, Z., Pokle, A., & Kolter, J. Z. (2023) · neural information processing systems · doi:10.52202/075280-1816 · Cited by 64
Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task
Lei, S. W., Gao, D., Wu, J. Z., Wang, Y., Liu, W., Zhang, M., & Shou, M. Z. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25208 · Cited by 63
SD-DiT: Unleashing the Power of Self-Supervised Discrimination in Diffusion Transformer *
Zhu, R., Pan, Y., Li, Y., Yao, T., Sun, Z., Mei, T., & Chen, C. W. (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/cvpr52733.2024.00806 · Cited by 64
RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection
He, Z., Chen, P., & Ho, T.-Y. (2024) · Transactions on machine learning research · doi:10.48550/arxiv.2405.20112 · Cited by 62
PixelDiT: Pixel Diffusion Transformers for Image GenerationPreprint
Yu, Y., Xiong, W., Nie, W., Sheng, Y., Liu, S., & Luo, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.20645 · Cited by 63
Explainability and vision foundation models: A survey
Kazmierczak, R., Berthier, É., Frehse, G., & Franchi, G. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103184 · Cited by 61
Li, T., Sun, Q., Fan, L., & He, K. (2025) · Transactions on machine learning research · doi:10.48550/arxiv.2502.17437 · Cited by 61
Video and Audio Deepfake Datasets and Open Issues in Deepfake Technology: Being Ahead of the Curve
Akhtar, Z., Pendyala, T. L., & Athmakuri, V. S. (2024) · Forensic Sciences · doi:10.3390/forensicsci4030021 · Cited by 60
3D generation on ImageNetPreprint
Skorokhodov, I., Siarohin, A., Xu, Y., Ren, J., Lee, H.-Y., Wonka, P., & Tulyakov, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.01416 · Cited by 60
“(e.g., Chan et al. (2022); Deng et al. (2022); Skorokhodov et al. (2022); Zhao et al. (2022); Schwarz et al. (2022)).”
BackgroundMethodInfluentialScalable Diffusion Models with State Space BackbonePreprint
Fei, Z., Fan, M., Yu, C., & Huang, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.05608 · Cited by 60
Generative Models: What Do They Know? Do They Know Things? Let's Find Out!Preprint
Du, X., Kolkin, N., Shakhnarovich, G., & Bhattad, A. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.17137 · Cited by 57
Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels
You, Z., Zhong, Y., Bao, F., Sun, J., Li, C., & Zhu, J. T. (2023) · neural information processing systems · doi:10.52202/075280-1883 · Cited by 58
Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook
Croitoru, F.-A., Hiji, A. I., Hondru, V., Ristea, N.-C., Irofti, P., Popescu, M., Rusu, C., Ionescu, R. T., Khan, F. S., & Shah, M. (2026) · ACM Computing Surveys · doi:10.1145/3833867 · Cited by 60
“[5] extend the StyleGAN model, presenting a method that leverages Pro-jected GAN training [62], progressive growing and classifier guidance [63], unlocking image synthesis at a resolution of 1024 × 1024.”
Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers
Cao, S., Yin, Y., Huang, L., Liu, Y., Zhao, X., Zhao, D., & Huang, K. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00677 · Cited by 52
Generative AI for design of nanoporous materials: review and future prospects
Xie, E., Wang, X., Siepmann, J. I., Chen, H., & Snurr, R. Q. (2025) · Digital Discovery · doi:10.1039/d5dd00221d · Cited by 53
PixelGen: Improving Pixel Diffusion with Perceptual SupervisionPreprint
Ma, Z., Xu, R., & Zhang, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.02493 · Cited by 52
“Adversarial losses [46] can improve realism but are unstable and difficult to optimize for pixel diffusion, so we do not use them.”
A Comprehensive Survey on Data-Efficient GANs in Image GenerationPreprint
Li, Z., Xia, B., Zhang, J., Wang, C., & Li, B. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2204.08329 · Cited by 52
“…distribution pg and real distribution pr. Mathematically, it is formulated as: min φ max θ f(φ, θ) = Ex∼pr [g1 (Dθ(x))] +Ez∼pz [g2 (Dθ (Gφ(z)))] , (1) 1StyleGAN-XL [Sauer et al., 2022], setting a new state-of-theart on large-scale image synthesis, needs 400 V100-days at a resolution of 5122 pixels.”
BackgroundRobust Unsupervised StyleGAN Image Restoration
Poirier‐Ginter, Y., & Lalonde, J. (2023) · 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/cvpr52729.2023.02135 · Cited by 50
One-step Diffusion Models with $f$-Divergence Distribution MatchingPreprint
Xu, Y., Nie, W., & Vahdat, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.15681 · Cited by 50
Diffusion Models without Classifier-free GuidancePreprint
Tang, Z., Bao, J., Chen, D., & Guo, B. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.12154 · Cited by 47
“This results in exaggerated truncation and mode dropping similar to (Karras et al., 2018; Brock et al., 2019; Sauer et al., 2022), since the samples are blindly pushed towards the regions with higher posterior probability.”
How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?
Koley, S., Bhunia, A. K., Sain, A., Chowdhury, P. N., Xiang, T., & Song, Y.-Z. (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/cvpr52733.2024.01595 · Cited by 46
“Our method could further be extended to scene-level SBIR with scene-level GANs [35, 60].”
MethodSelf-Improving Diffusion Models with Synthetic DataPreprint
Alemohammad, S., Humayun, A. I., Agarwal, S., Collomosse, J. P., & Baraniuk, R. G. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.16333 · Cited by 46
“We also compare with generative adversarial networks (GANs) such as StyleGAN-XL (Sauer et al., 2022) and StyleGAN-2-ADA (Karras et al., 2020).”
ResultDiffeomorphic Counterfactuals With Generative Models
Dombrowski, A.-K., Gerken, J. E., Müller, K., & Kessel, P. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3339980 · Cited by 44
“NotethattheStyleGANcanalsobe used at the same resolution even for the more diverse ImageNet dataset if required, see [72].”
Defect Image Sample Generation With Diffusion Prior for Steel Surface Defect Recognition
Tai, Y., Yang, K., Peng, T., Huang, Z., & Zhang, Z. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3482362 · Cited by 44
“Then the models [43], [44], [45] derived from it, show satisfactory generative ability and have been widely used in general image generation tasks.”
Weed image augmentation by ControlNet-added stable diffusion for multi-class weed detection
Deng, B., & Lu, Y. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110123 · Cited by 45
Exploring Precision and Recall to assess the quality and diversity of LLMs
Bronnec, F. L., Vérine, A., Négrevergne, B., Chevaleyre, Y., & Allauzen, A. (2024) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2024.acl-long.616 · Cited by 43
Fill-Up: Balancing Long-Tailed Data with Generative ModelsPreprint
Shin, J., Kang, M., & Park, J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.07200 · Cited by 44
“Simulation pipelines from 3D engines [68, 69] or pretrained class-conditional GANs have been utilized as data sources.”
BackgroundInfluentialGenerative Adversarial Network Applications in Industry 4.0: A Review
Akar, C. A., Massih, R. A., Yaghi, A., Khalil, J., Kamradt, M., & Makhoul, A. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-023-01966-9 · Cited by 42
NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering
Huang, Z., Qiu, X., Ma, Y., Zhou, Y., Chen, J., Zhang, H., Zhang, C., & Li, X. (2025) · neural information processing systems · doi:10.52202/085713-0866 · Cited by 42
“The synthesis of images has emerged as a fundamental challenge in computer vision [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12].”
Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step
Zhou, M., Zheng, H., Gu, Y., Wang, Z., & Huang, H. (2024) · International Conference on Learning Representations · doi:10.48550/arxiv.2410.14919 · Cited by 42
Do Text-Free Diffusion Models Learn Discriminative Visual Representations?
Mukhopadhyay, S., Gwilliam, M., Yamaguchi, Y., Agarwal, V., Padmanabhan, N., Swaminathan, A., Zhou, T., Ohya, J., & Shrivastava, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73027-6_15 · Cited by 41
Generative Visual Prompt: Unifying Distributional Control of Pre-Trained Generative Models
Wu, C. H., Motamed, S., Srivastava, S., & Torre, F. D. D. L. (2022) · neural information processing systems · doi:10.52202/068431-1629 · Cited by 41
A Survey of Multimodal Controllable Diffusion Models
Jiang, R., Zheng, G., Li, T., Yang, T., Wang, J., & Li, X. (2024) · Journal of Computer Science and Technology · doi:10.1007/s11390-024-3814-0 · Cited by 40
Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance
Kawar, B., Ganz, R., & Elad, M. (2023) · Transactions on machine learning research · doi:10.48550/arxiv.2208.08664 · Cited by 42
“for use in classifier-guided GAN training (Sauer et al., 2022); (iii) extending our proposed technique to unlabeled datasets; and (iv) seeking better sources of perceptually aligned gradients (Ganz et al.”
MethodImage Synthesis Under Limited Data: A Survey and Taxonomy
Yang, M., & Wang, Z. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02357-y · Cited by 39
“Moreover, they extended FAML via applying a self-supervised contrastive learning strategy to the fast adaptive meta-learning framework [189], which improved both the speed of model convergence and the synthesis performance.”
Unlocking Dataset Distillation with Diffusion Models
Moser, B. B., Raue, F., Palacio, S., Frolov, S., & Dengel, A. R. (2025) · neural information processing systems · doi:10.52202/085713-2434 · Cited by 39
“The optimization objective becomes 3 Related Work GAN Priors (GLaD): GLaD [5] pioneered distillation with generative priors using a pre-trained StyleGAN-XL [30].”
On the generation of realistic synthetic petrographic datasets using a style-based GAN
Ferreira, I., Gutierrez, L. H. O., & Koeshidayatullah, A. (2022) · Scientific Reports · doi:10.1038/s41598-022-16034-4 · Cited by 40
Polynomial Implicit Neural Representations For Large Diverse Datasets
Singh, R., Shukla, A., & Turaga, P. K. (2023) · 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/cvpr52729.2023.00203 · Cited by 39
“We follow the training scheme of the StyleGAN-XL method [42] and use a projected discriminator based on the pre-trained classifiers (DeiT [51] and EfficientNet [48]) with an additional classifier guidance loss [8].”
MethodInfluentialThe Evolution of Dataset Distillation: Toward Scalable and Generalizable SolutionsPreprint
Liu, P., & Du, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.05673 · Cited by 39
“Building on this shift to latent spaces, George et al. [42] proposed GlaD, which leverages the latent spaces of generative models like StyleGAN-XL [43].”
Image Generation Diversity Issues and How to Tame Them
Dombrowski, M., Zhang, W., Cechnicka, S., Reynaud, H., & Kainz, B. (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/cvpr52734.2025.00288 · Cited by 38
“Precision and recall [26] are most established in literature [12, 36, 41, 46].”
Language-Guided Image Tokenization for Generation
Zha, K., Yu, L., Fathi, A., Ross, D. A., Schmid, C., Katabi, D., & Gu, X. (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/cvpr52734.2025.01465 · Cited by 37
“Generative learning of pixels has been explored under adversarial [3, 40], autoregressive [6], and diffusion [9, 18, 22] setups.”
GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild
Wang, C., Serrano, A., Pan, X., Chen, B., Myszkowski, K., Seidel, H., Theobalt, C., & Leimkühler, T. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00964 · Cited by 37
“Recon-10510 Vanilla GAN [20, 62, 36] Unstructured LDRs ✗ ✗ ✓ ✗ Direct ITM [16, 47, 19, 45, 71, 70, 10] Paired LDR-HDR images ✓ ✗ ✗ Weak Indirect ITM [14, 41, 42, 43, 28] Paired LDR exposure stacks 1 Capable of generating HDR images or performing inverse tone mapping.”
BackgroundMethodInfluentialScalable Autoregressive Image Generation with MambaPreprint
Li, H., Yang, J., Wang, K., Qiu, X., Chou, Y., Li, X., & Li, G. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.12245 · Cited by 37
DiffMoE: Dynamic Token Selection for Scalable Diffusion TransformersPreprint
Shi, M., Yuan, Z., Yang, H., Wang, X., Zheng, M., Tao, X., Zhao, W., Zheng, W., Zhou, J., Lu, J., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.14487 · Cited by 37
The Platonic Representation Hypothesis
Huh, M., Cheung, B., Wang, T., & Isola, P. (2024) · arXiv · doi:10.48550/arxiv.2405.07987 · Cited by 35
“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.”
BackgroundWang, Z., Wang, J., Liu, Z., & Qiu, Q. (2023) · 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/cvpr52729.2023.02162 · Cited by 36
Discovering Failure Modes of Text-guided Diffusion Models via Adversarial SearchPreprint
Liu, Q., Kortylewski, A., Bai, Y., Bai, S., & Yuille, A. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.00974 · Cited by 35
“We also test on StyleGAN-XL [34] to show its general applicability.”
A study of enhanced visual perception of marine biology images based on diffusion-GAN
Yao, F., Zhang, H., Gong, Y., Zhang, Q., & Pan, X. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-01832-w · Cited by 34
Zhong, X., Fang, H., Chen, B., Gu, X., Qiu, M., Qi, S., & Xia, S. (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/cvpr52734.2025.02836 · Cited by 34
“GLaD employs GAN (e.g., StyleGAN-XL [34]) as a prior and significantly improves the cross-architecture performance of the synthetic dataset by selecting the feature domain of GAN’s intermediate layers as the optimization space.”
Draft-And-Revise: Effective Image Generation with Contextual RQ-Transformer
Lee, D., Kim, C., Kim, S., Cho, M., & Han, W.-S. (2022) · neural information processing systems · doi:10.52202/068431-2184 · Cited by 34
Towards a Scalable Reference-Free Evaluation of Generative Models
Ospanov, A., Zhang, J., Jalali, M., Cao, X., Bogdanov, A., & Farnia, F. (2024) · neural information processing systems · doi:10.52202/079017-3841 · Cited by 33
VQ3D: Learning a 3D-Aware Generative Model on ImageNet
Sargent, K., Koh, J. Y., Zhang, H., Chang, H., Herrmann, C., Srinivasan, P. P., Wu, J., & Sun, D. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00391 · Cited by 33
“However, GANs are unstable and challenging to scale to large diverse datasets [3, 35].”
BackgroundNext Patch Prediction for AutoRegressive Visual Generation
Pang, Y., Peng, J. I. N., Yang, S., Zhu, B. B., Lin, B., Feng, C., Tang, Z., Chen, L., Tay, F. E. H., Lim, S.-N., et al. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i10.37774 · Cited by 33
So-Fake: Benchmarking and Explaining Social Media Image Forgery DetectionPreprint
Huang, Z., Li, X., Yang, X., Peng, B., Huang, X., Wu, B., Tao, D., Yang, M.-H., & Cheng, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.18660 · Cited by 35
One-Step Generative Modeling via Wasserstein Gradient FlowsPreprint
Han, J., Li, P., Guo, Q., Xu, R., Ermon, S., & Candès, E. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.11755 · Cited by 33
Masked-attention diffusion guidance for spatially controlling text-to-image generation
Endo, Y. (2023) · The Visual Computer · doi:10.1007/s00371-023-03151-y · Cited by 32
“There have been various GAN-based methods, such as PGGAN [25], BigGAN [8], and StyleGAN [23, 24, 26, 44], that can generate high-quality and diverse images.”
InfluentialCan diffusion model conditionally generate astrophysical images?
Zhao, X., Ting, Y.-S., Diao, K., & Mao, Y. (2023) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stad2778 · Cited by 32
Exact Diffusion Inversion via Bidirectional Integration Approximation
Zhang, G., Lewis, J. P., & Kleijn, W. B. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72998-0_2 · Cited by 32
New Insights for the Stability-Plasticity Dilemma in Online Continual LearningPreprint
Jung, D., Lee, D., Hong, S., Jang, H., Bae, H., & Yoon, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.08741 · Cited by 32
Flow Generator MatchingPreprint
Huang, Z., Geng, Z., Luo, W., & Qi, G.-J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.19310 · Cited by 32
Personalized Face Inpainting with Diffusion Models by Parallel Visual Attention
Xu, J., Motamed, S., Vaddamanu, P., Wu, C., Häne, C., Bazin, J., & la Torre, F. D. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00535 · Cited by 31
“[47, 48].”
WildFake: A Large-Scale and Hierarchical Dataset for AI-Generated Images Detection
Hong, Y., Feng, J., Chen, H., Lan, J., Zhu, H., Wang, W., & Zhang, J. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i4.32363 · Cited by 31
Modulating Pretrained Diffusion Models for Multimodal Image Synthesis
Ham, C., Hays, J. H., Lu, J., Singh, K. K., Zhang, Z., & Hinz, T. (2023) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3588432.3591549 · Cited by 32
“One notable example is the StyleGAN series [Karras et al. 2020a, 2021, 2019, 2020b; Sauer et al. 2022], which has served as a source of inspiration for many other conditional generation works.”
BackgroundNoisyTwins: Class-Consistent and Diverse Image Generation Through StyleGANs
Rangwani, H., Bansal, L., Sharma, K., Karmali, T., Jampani, V., & Babu, R. V. (2023) · 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/cvpr52729.2023.00580 · Cited by 32
UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields
Yang, Y., Yang, Y., Guo, H., Xiong, R., Wang, Y., & Liao, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00844 · Cited by 31
“Conditional Image synthesis: In recent years, Generative Adversarial Networks [15, 28, 29, 26, 27, 51] have achieved impressive results in photorealistic image synthesis.”
BackgroundEfficient Diffusion Transformer with Step-Wise Dynamic Attention Mediators
Pu, Y., Xia, Z., Guo, J., Han, D., Li, Q., Li, D., Yuan, Y., Li, J., Han, Y., Song, S., et al. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72633-0_24 · Cited by 33
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
Kim, D., Lai, C.-H., Liao, W.-H., Takida, Y., Murata, N., Uesaka, T., Mitsufuji, Y., & Ermon, S. (2024) · neural information processing systems · doi:10.52202/079017-0606 · Cited by 31
MAUVE Scores for Generative Models: Theory and PracticePreprint
Pillutla, K., Liu, L., Thickstun, J., Welleck, S., Swayamdipta, S., Zellers, R., Oh, S., Choi, Y., & Harchaoui, Z. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.14578 · Cited by 31
EXION: Exploiting Inter-and Intra-Iteration Output Sparsity for Diffusion Models
Heo, J., Putra, A., Yoon, J., Yune, S., Lee, H.-G., Kim, J.-H., & Kim, J. (2025) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca61900.2025.00034 · Cited by 31
“For example, Stable Diffusion generates images from text prompts with better quality and diversity compared to StyleGAN-XL [37], a popular generative adversarial network.”
Structure-Guided Adversarial Training of Diffusion Models
Yang, L., Qian, H., Zhang, Z., Liu, J., & Cui, B. (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/cvpr52733.2024.00693 · Cited by 30
Efficient Image Generation with Variadic Attention Heads
Walton, S., Hassani, A., Xu, X., Wang, Z., & Shi, H. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00306 · Cited by 30
“By increasing the information gain through Hydra-NA we can achieve higher performance without the scaling that other methods like StyleGAN-XL require [55].”
InfluentialEquilibrium Matching: Generative Modeling with Implicit Energy-Based ModelsPreprint
Wang, R., & Du, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.02300 · Cited by 31
“We compare Equilibrium Matching with prior generative methods, including StyleGAN (Sauer et al., 2022), VDM++ (Kingma and Gao, 2023), DiT (Peebles and Xie, 2023), and SiT (Ma et al., 2024).”
Transition Models: Rethinking the Generative Learning ObjectivePreprint
Wang, Z., Zhang, Y., Yue, X., Yue, X., Li, Y., Ouyang, W., & Bai, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.04394 · Cited by 30
A Case for Synthetic Data in Regulatory Decision‐Making in Europe
Alloza, C., Knox, B., Raad, H., Aguilà, M., Coakley, C., Mohrová, Z., Boin, É., Bénard, M., Davies, J., Jacquot, E., et al. (2023) · Clinical Pharmacology & Therapeutics · doi:10.1002/cpt.3001 · Cited by 28
Gaussian Splatting Decoder for 3D-aware Generative Adversarial Networks
Barthel, F., Beckmann, A., Morgenstern, W., Hilsmann, A., & Eisert, P. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00794 · Cited by 28
“Over the last few years, there have been drastic improvements to 2D [14–16, 37 ] and 3D [2, 6– 8, 33, Recently introduced, 3D Gaussian Splatting (3DGS) [19] provides a novel explicit 3D scene representation, enabling high-quality renderings at high frame rates.”
LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer
Yu, N., Chen, C.-C., Chen, Z., Meng, R., Wu, G., Josel, P., Niebles, J. C., Xiong, C., & Xu, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72661-3_10 · Cited by 28
Towards Diverse and Faithful One-Shot Adaption of Generative Adversarial Networks
Zhang, Y., Yao, M., Wei, Y., Ji, Z., Bai, J., & Zuo, W. (2022) · neural information processing systems · doi:10.52202/068431-2703 · Cited by 28
Privacy-Preserving Synthetic Continual Semantic Segmentation for Robotic Surgery
Xu, M., Islam, M., Bai, L., & Ren, H. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3364969 · Cited by 27
“To address the privacy restrictions imposed, we utilize StyleGAN-XL [47], consisting of the generator and the discriminator neural networks, to generate the tissue image as background.”
MethodInfluentialDomain Re-Modulation for Few-Shot Generative Domain Adaptation
Wu, Y., Li, Z., Wang, C., Zheng, H., Zhao, S., Li, B., & Tao, D. (2023) · neural information processing systems · doi:10.52202/075280-2497 · Cited by 27
Boomerang: Local sampling on image manifolds using diffusion models
Luzi, L., Mayer, P. M., Casco-Rodriguez, J., Siahkoohi, A., & Baraniuk, R. G. (2022) · Transactions on machine learning research · doi:10.48550/arxiv.2210.12100 · Cited by 27
“…a tremendous rise in popularity and applications over the past decade, ranging from image synthesis (Grcić et al., 2021; Dhariwal & Nichol, 2021; Sauer et al., 2022), audio generation (van Original image Back to t = 0 prompt = “person” Back to t = 0 prompt = “person” Back to t = 0 prompt =…”
BackgroundHalton Scheduler For Masked Generative Image Transformer
Besnier, V., Chen, M., Hurych, D., Junior, E. A. D. V., & Cord, M. (2025) · International Conference on Learning Representations · doi:10.48550/arxiv.2503.17076 · Cited by 29
DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation
Phung, H., Dao, Q. T., Dao, T., Phan, H., Metaxas, D., & Tran, A. N. (2024) · neural information processing systems · doi:10.52202/079017-1037 · Cited by 26
Balanced Training for Sparse GANs
Wang, Y., Wu, J., Hovakimyan, N., & Sun, R. (2023) · neural information processing systems · doi:10.52202/075280-0600 · Cited by 26
“Generative adversarial networks (GANs) [Goodfellow et al., 2020, Brock et al., 2018, Sauer et al., 2022, Lee et al., 2022] are a type of generative model that has gained significant attention in recent years due to their impressive performance in image-generation tasks.”
BackgroundUnified Continuous Generative ModelsPreprint
Sun, P., Jiang, Y., & Lin, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.07447 · Cited by 26
Synthesis of multi-band reflective polarizing metasurfaces using a generative adversarial network
Naseri, P., Goussetis, G., Fonseca, N. J. G., & Hum, S. V. (2022) · Scientific Reports · doi:10.1038/s41598-022-20851-y · Cited by 25
Kim, P. J., Jang, Y., Kim, J., & Yoo, J. (2023) · neural information processing systems · doi:10.52202/075280-0344 · Cited by 25
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.