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 301–400 of 793
Environmental Landscape Art Design Based on Visual Neural Network Model in Rural Construction
Wang, L., & He, Y. (2023) · Ecological Chemistry and Engineering S · doi:10.2478/eces-2023-0028 · Cited by 12
Statistics Enhancement Generative Adversarial Networks for Diverse Conditional Image Synthesis
Zuo, Z., Li, A., Zhi-zhong, W., Zhao, L., Dong, J., Wang, X., & Wang, M. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3348471 · Cited by 12
“…works have been proposed to resist the problem by designing advanced network architectures [36], [63], [64], [65], [66], [67], [68], [69], [70], [71], introducing better training objectives or regularization [41], [72], [73], [74], [75], [76], [77], [78], [79], [80], [81], [82], [83], [84],…”
BackgroundVerma, A., Badal, T., & Bansal, A. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104077 · Cited by 12
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
Ni, Z., Wang, Y., Zhou, R., Han, Y., Guo, J., Liu, Z., Yao, Y., & Huang, G. M. (2024) · neural information processing systems · doi:10.52202/079017-2870 · Cited by 12
Learning to Jump: Thinning and Thickening Latent Counts for Generative ModelingPreprint
Chen, T., & Zhou, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.18375 · Cited by 12
“…2017; Gulrajani et al., 2017; Miyato et al., 2018; Mescheder et al., 2018), generation fidelity (Radford et al., 2015; Brock et al., 2019; Karras et al., 2019; Sauer et al., 2022), and mode coverage and data efficiency (Zhao et al., 2020; Karras et al., 2020; Yang et al., 2021; Wang et al., 2022).”
BackgroundSTREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models
Kim, P. J., Kim, S., & Yoo, J. (2024) · International Conference on Learning Representations · doi:10.48550/arxiv.2403.09669 · Cited by 12
“Recent breakthroughs in powerful generative models [10, 16,19] have ushered in an era of generating highly realistic images, largely due to in-sightful evaluation metrics [7,11,12,15,18] that have shaped their progress.”
BackgroundLiu, G., Wang, Y., Feng, Z., Wu, Q., Tang, L., Gao, Y., Li, Z., Cui, S. R., McAuley, J., Yang, Z., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.19009 · Cited by 12
“Similar to StyleGAN-XL, we conduct all the experiments in the resolution 256 × 256 and calculate FID with resolution 128 × 128 .”
MethodToward Guidance-Free AR Visual Generation via Condition Contrastive Alignment
Chen, H., Su, H., Sun, P., & Zhu, J. (2024) · International Conference on Learning Representations · doi:10.48550/arxiv.2410.09347 · Cited by 12
“…2019; Song et al., 2020; Dhariwal & Nichol, 2021; Kingma & Gao, 2024) are representative modeling methods for visual content generation, widely recognized for their ability to produce realistic and artistic images (Sauer et al., 2022; Ho et al., 2022; Ramesh et al., 2022; Podell et al., 2023).”
BackgroundMulti-student Diffusion Distillation for Better One-step GeneratorsPreprint
Song, Y., Lorraine, J., Nie, W., Kreis, K., & Lucas, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.23274 · Cited by 12
“It surpasses even the EDM teacher, StyleGAN-XL [57], the multi-step RIN [23] due to the adversarial loss.”
PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion
Guo, Z., Ma, L., He, Y., Fu, X., Fu, J., Huang, J. W., & Li, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_24 · Cited by 11
VeRi3D: Generative Vertex-based Radiance Fields for 3D Controllable Human Image Synthesis
Chen, X., Huang, J., Bin, Y., Yu, L., & Liao, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00825 · Cited by 11
“GAN-based Image Synthesis: Generative adversarial networks [14] have achieved 2D image synthesis with high visual fidelity [36, 21, 23, 24, 22, 52, 64].”
Multi-distribution mixture generative adversarial networks for fitting diverse data sets
Yang, M., Tang, J., Dang, S., Chen, G., & Chambers, J. A. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123450 · Cited by 11
Data-agnostic Face Image Synthesis Detection using Bayesian CNNs
Leyva, R., Sánchez, V., Epiphaniou, G., & Maple, C. R. (2024) · Pattern Recognition Letters · doi:10.1016/j.patrec.2024.04.008 · Cited by 11
Analyzing the latent space of GAN through local dimension estimation for disentanglement evaluation
Choi, J., Hwang, G., Cho, H., & Kang, M. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110914 · Cited by 11
Data-to-Model Distillation: Data-Efficient Learning Framework
Sajedi, A., Khaki, S., Liu, L., Amjadian, E., Lawryshyn, Y., & Plataniotis, K. N. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72775-7_25 · Cited by 11
Oehri, S., Ebert, N., Abdullah, A., Stricker, D., & Wasenmüller, O. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78166-7_12 · Cited by 12
FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
Zhao, W., Shi, M., Yu, X., Zhou, J., & Lu, J. (2024) · neural information processing systems · doi:10.52202/079017-0135 · Cited by 11
Video Coding using Learned Latent GAN Compression
Shukor, M., Damodaran, B. B., Yao, X., & Pierre Hellier, J. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548219 · Cited by 11
“Recently, [9] has proposed to extend StyleGAN to ImageNet classes.”
BackgroundConditional generative data-free knowledge distillation
Yu, X., Yan, L., Yang, Y., Libo, Z. H. O. U., & Ou, L. (2023) · Image and Vision Computing · doi:10.1016/j.imavis.2023.104627 · Cited by 11
LEAD: Min-Max Optimization from a Physical PerspectivePreprint
Hemmat, R. A., Mitra, A., Lajoie, G., & Mitliagkas, I. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.13846 · Cited by 11
“Note that state of the art performance in recent work such as Style-GAN based models (Sauer et al., 2022; Kang et al., 2021; Lee et al., 2021) or BigGAN based models (Brock et al.”
BackgroundScalable Training for Vector-Quantized Networks with 100% Codebook UtilizationPreprint
Chang, Y., Qin, J., Qiao, L., Wang, X., Zhu, Z. D., Ma, L., & Wang, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.10140 · Cited by 11
PGC: Peak-Guided Calibration for Generalizable AI-Generated Image DetectionPreprint
Zhou, X., Fei, J., Yu, P., Xie, J., Cheng, C., & Xia, Z. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.21207 · Cited by 11
Are Images Indistinguishable to Humans Also Indistinguishable to Classifiers?
You, Z., Zhang, X., Guo, H., Wang, J., & Li, C. (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/cvpr52734.2025.02681 · Cited by 10
Souza, M., Zheng, Y., Kang, K., Mishra, Y. N., Fu, Q., & Heidrich, W. (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/cvpr52734.2025.02635 · Cited by 10
“We employ the loss functions specified in Equation 1, while reducing the learning rate to 10 − 5 , to optimize performance and accuracy in real-world applications.”
Regional Traditional Painting Generation Based on Controllable Disentanglement Model
Zhao, Y., Li, H., Zhang, Z., Chen, Y., Liu, Q., & Zhang, X. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3298811 · Cited by 10
“Some StyleGAN-based methods [23], [24], [25] utilize a hierarchical generator and pixel-wise noise injection to achieve disentan-glement for natural image generation, which can make the transition of the combination of content and style smoother.”
MethodA Hybrid Generator Architecture for Controllable Face Synthesis
Mensah, D., Kim, N. H., Aittala, M., Laine, S., & Lehtinen, J. (2023) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3588432.3591563 · Cited by 10
Benchmarking the Fairness of Image Upsampling Methods
Laszkiewicz, M., Daunhawer, I., Vogt, J. E., Fischer, A., & Lederer, J. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658921 · Cited by 10
A Software Ecosystem for Deploying Deep Learning in Gravitational Wave Physics
Gunny, A., Rankin, D. S., Harris, P. C., Katsavounidis, E., Marx, E., Saleem, M., Coughlin, M. W., & Benoit, W. (2022) · doi:10.1145/3526058.3535454 · Cited by 10
“This research has emerged in a decade in which deep learning has been shown more broadly to achieve state-of-the-art results in fields such as computer vision [36, 37], natural language processing [22, 31], generative modelling [33], and complex game playing [13, 28].”
BackgroundSynthesizing Anyone, Anywhere, in Any Pose
Hukkelås, H., & Lindseth, F. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00399 · Cited by 10
“Recently introduced Projected GANs [53] use pre-trained feature networks for the discriminator to reduce training time and improve image quality, which was later extended for high-resolution image synthesis on the ImageNet [6] dataset [54].”
BackgroundMethodInfluentialStraIT: Non-autoregressive Generation with Stratified Image TransformerPreprint
Qian, S., Chang, H., Li, Y., Zhang, Z., Jia, J., & Zhang, H. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.00750 · Cited by 10
“StyleGAN-XL ADM-U-G MaskGIT Token Critic Quality Diversity Figure 4.”
MethodInfluential3D GANs and Latent Space: A comprehensive surveyPreprint
Tata, S. P., & Mishra, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.03932 · Cited by 10
“Some of its areas of application include generating examples for image datasets [117, 133, 141, 34, 64, 132, 33, 99, 6, 45], human faces [69, 88, 53, 83, 91], cartoon and anime characters[116, 66], image-to-image translation [57, 21, 153, 172, 177, 122, 86, 67, 148], text-to-image translation [76,…”
Single-Model Attribution of Generative Models Through Final-Layer InversionPreprint
Laszkiewicz, M., Ricker, J., Lederer, J., & Fischer, A. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.06210 · Cited by 10
“Specifically, G consists of StyleGAN2 (Karras et al., 2021), StyleGAN-XL (Sauer et al., 2022), StyleNAT (Walton et al., 2022), StyleSwin (Zhang et al., 2022), and of FFHQ images.”
BackgroundImproving Autoregressive Image Generation through Coarse-to-Fine Token PredictionPreprint
Guo, Z., Zhang, K., & Shieh, M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.16194 · Cited by 10
Image Generation with a Sphere EncoderPreprint
Yue, K., Jia, M., Hou, J., & Goldstein, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.15030 · Cited by 10
“Pixel-space generation is common for GANs (Karras et al., 2020; Kang et al., 2023; Sauer et al., 2022; Brock et al., 2019; 2018) but challenging for diffusion models due to the high dimensionality of pixel space (Child, 2019; Van den Oord et al., 2016; Chen et al., 2020; Hawthorne et al., 2022; Yu…”
Rosetta Neurons: Mining the Common Units in a Model Zoo
Dravid, A., Gandelsman, Y., Efros, A. A., & Shocher, A. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00185 · Cited by 9
“We add our loss term to the optimization, where the Rosetta Neurons are calculated from 3 sets of matches with StyleGAN-XL: matching to DINO-RN, matching to CLIP-RN, and matching across all the discriminative models in Table 2.”
MethodInfluentialA brief study of generative adversarial networks and their applications in image synthesis
Sharma, H., & Das, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16175-2 · Cited by 9
“This is the first GAN variant which was capable of generating images at high scale resolution 1024x1024, proposed by Axel et al. [61], StyleGAN-XL is capable of inversion operation and image manipulation tasks.”
Urban-StyleGAN: Learning to Generate and Manipulate Images of Urban Scenes
Eskandar, G., Farag, Y., Yenamandra, T., Cremers, D., Guirguis, K., & Yang, B. (2023) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv55152.2023.10186698 · Cited by 9
Consistency-GAN: Training GANs with Consistency Model
Wang, Y., Pang, M., Chen, S., & Rao, H. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i14.29503 · Cited by 9
“…2014; Radford, Metz, and Chintala 2016; Brock, Donahue, and Simonyan 2018; Wu et al. 2019; Karras, Laine, and Aila 2019; Karras et al. 2020; Pang et al. 2021a,b; Sauer et al. 2021; Sauer, Schwarz, and Geiger 2022) demonstrate remarkable capabilities in generating realistic and high-quality samples.”
BackgroundImproving the Fairness of the Min-Max Game in GANs Training
Zhang, Z., Yang, H., Wang, H., & McLoone, S. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00289 · Cited by 9
“To improve the training of GANs, GANs with multiple discriminators [32, 33, 48, 49] have been proposed.”
BackgroundHwang, J., Lee, J., & Lee, 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/cvpr52733.2024.00836 · Cited by 9
“We employ generated datasets produced by various generative models including GANs [3, 8, 10, 18, 26, 27, 29, 30, 45, 51, 52, 57, 58, 61, 62], VAEs [32, 36], a flow-based generative model [11], and diffusion models [5, 6, 15, 16, 25, 44, 47, 56, 60] from dgm-eval [54] and utilize 10000 generated…”
Wang, Y., & Deng, L. (2024) · IEEE Access · doi:10.1109/access.2024.3491167 · Cited by 9
“Furthermore, StyleGAN3 [33] and StyleGAN-XL [34] show outstanding performance on large-scale image synthesis with high resolution, meanwhile, the difficulty in the training process of StyleGANs is decreasing significantly.”
One-for-All: Towards Universal Domain Translation With a Single StyleGAN
Du, Y., Zhan, J., Li, X., Dong, J., Chen, S., Yang, M., & He, S. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3530099 · Cited by 9
“DiFa, which fine-tunes the AFHQ generator, produces 512 × 512 images.”
Learning to Integrate Diffusion ODEs by Averaging the Derivatives
Liu, W., & Yue, X. (2025) · neural information processing systems · doi:10.52202/085713-4462 · Cited by 9
Regularizing Neural Networks with Meta-Learning Generative Models
Yamaguchi, S., Chijiwa, D., Kanai, S., Kumagai, A., & Kashima, H. (2023) · neural information processing systems · doi:10.52202/075280-1190 · Cited by 9
Smoothness Similarity Regularization for Few-Shot GAN Adaptation
Sushko, V., Wang, R., & Gall, J. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00651 · Cited by 9
“Generative adversarial networks (GANs) have been shown to be powerful at various image synthesis tasks [5, 29, 4, 14, 28, 27].”
BackgroundText-Conditioned Sampling Framework for Text-to-Image Generation with Masked Generative Models
Lee, J., Jang, S., Jo, J., Yoon, J., Kim, Y., Kim, J.-H., Ha, J.-W., & Hwang, S. J. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02125 · Cited by 9
“Although many recent works have achieved success in synthesizing highquality images [18, 33] with plausible class-alignment in class-conditional cases [4, 8], text-to-image (T2I) genera-”
Advancements in Synthetic Generation of Contactless Palmprint Biometrics Using StyleGAN Models
Chowdhury, A. M. M., Khondkar, M. J. A., & Imtiaz, M. H. (2024) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp4030032 · Cited by 9
G3DR: Generative 3D Reconstruction in ImageNet
Reddy, P., Elezi, I., & Deng, 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/cvpr52733.2024.00922 · Cited by 9
RadImageGAN – A Multi-modal Dataset-Scale Generative AI for Medical Imaging
Liu, Z., Smith, A. P., Lautin, A., Zhou, J., Yoo, M., Sullivan, M., Li, H., Deyer, L., Zhou, A., Yang, A., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-82007-6_17 · Cited by 9
NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions
Shahbazi, M., Ntavelis, E., Tonioni, A., Collins, E., Paudel, D. P., Danelljan, M., & Gool, L. V. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00311 · Cited by 9
Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models
Zhang, P., Liu, H., Li, C., Xie, X., Kim, S., & Wang, H. (2024) · International Conference on Learning Representations · doi:10.48550/arxiv.2308.10632 · Cited by 10
“We conduct ablation study on the generator choice to agree on the performance ranking in Table 1 and Table 2 (Dhariwal & Nichol, 2021), and GAN like StyleGAN-XL (Sauer et al., 2022).”
MethodGaussian Harmony: Attaining Fairness in Diffusion-based Face Generation ModelsPreprint
Pal, B., Kannan, A., Kathirvel, R. P., O’Toole, A. J., & Chellappa, R. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.14976 · Cited by 9
“Through iterative training, GANs learn to map complex patterns from the latent space to produce realistic data, and were previously considered state-of-the-art in various applications [31], [38], [46] including synthetic face generation [27], [14].”
BackgroundMotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion
Susladkar, O., Gupta, J. S., Sehgal, C., Mittal, S., & Singhal, R. (2024) · International Conference on Learning Representations · doi:10.48550/arxiv.2410.07659 · Cited by 9
FlowDCN: Exploring DCN-like Architectures for Fast Image Generation with Arbitrary ResolutionPreprint
Wang, S., Li, Z., Song, T., Li, X., Ge, T., Zheng, B., & Wang, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.22655 · Cited by 9
“Diffusion models [1, 2, 3, 4, 5] have recently emerged as a highly promising foundation for training algorithms in image generation, outperforming GAN-based models [6, 7] and Auto-Regressive models [8] by a significant margin.”
LiT: Delving into a Simple Linear Diffusion Transformer for Image GenerationPreprint
Wang, J., Kang, N., Yao, L., Chen, M., Wu, C., Zhang, S., Xue, S., Liu, Y., Wu, T., Liu, X., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.12976 · Cited by 9
The Vendiscope: An Algorithmic Microscope For Data CollectionsPreprint
Pasarkar, A. P., & Dieng, A. B. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.10828 · Cited by 9
“In all, we tested 8 GAN models: ACGAN (Odena et al., 2017), BigGAN (Brock et al., 2019), LOGAN (Wu et al., 2019), ReACGAN (Kang et al., 2021), MHGAN, (Turner et al., 2019), WGAN-GP (Gulrajani et al., 2017), StyleGAN2-ada (Karras et al., 2020), and StyleGAN2-XL (Sauer et al., 2022).”
Hierarchical Masked Autoregressive Models with Low-Resolution Token PivotsPreprint
Zheng, G., Li, Y., Pan, Y., Deng, J., Yao, T. S., Zhang, Y., & Mei, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.20288 · Cited by 9
MeanFlow Transformers with Representation AutoencodersPreprint
Hu, Z., Lai, C.-H., Wu, G., Mitsufuji, Y., & Ermon, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.13019 · Cited by 9
BlobGAN-3D: A Spatially-Disentangled 3D-Aware Generative Model for Indoor Scenes
Wang, Q., Wang, Y., Birsak, M., & Wonka, P. (2023) · arXiv (Cornell University) · doi:10.25781/kaust-895b2 · Cited by 9
Data expansion for industrial defect detection with diffusion prior
Tai, Y., & Zhang, Z. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111835 · Cited by 8
SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows
Zhao, Q., Zheng, G., Yang, T., Zhu, R., Leng, X., Gould, S. J., & Zheng, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37577-3_37 · Cited by 8
DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
Ai, Y., Fan, Q., Hu, X., Yang, Z., He, R., & Huang, H. (2025) · neural information processing systems · doi:10.52202/085713-4119 · Cited by 8
Continuous Adversarial Flow Models
Lin, S., Yang, C., Lin, Z., Chen, H., & Fan, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_36 · Cited by 8
CubeGAN: Omnidirectional Image Synthesis Using Generative Adversarial Networks
May, C., & Aliaga, D. G. (2023) · Computer Graphics Forum · doi:10.1111/cgf.14755 · Cited by 8
“, [SSG22] and Figure 6), but do perform well on highly structured datasets such as faces [KLA19] and with sufficient training time.”
BackgroundOptimizing Generative Adversarial Network (GAN) Models for Non-Pneumatic Tire Design
Seong, J., Ji, S.-M., Choi, D.-H., Lee, S., & Lee, S. (2023) · Applied Sciences · doi:10.3390/app131910664 · Cited by 8
Alias-Free Co-modulated Network for Cross-Modality Synthesis and Super-Resolution of MR Images
Song, Z., Wang, X., Zhao, X., Wang, S., Shen, Z., Zhuang, Z., Liu, M., Wang, Q., & Zhang, L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43999-5_7 · Cited by 8
Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation
Yue, X., Wang, Z., Wang, Y., Zhang, W., Liu, X., Ouyang, W., Bai, L., & Zhou, L. (2025) · neural information processing systems · doi:10.52202/085713-4804 · Cited by 8
Cycles Improve Conditional Generators: Synthesis and Augmentation for Data Mining
Moore, A. M., Paffenroth, R. C., Ngo, K. T., & Uzarski, J. R. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-22137-8_26 · Cited by 8
The Beauty or the Beast: Which Aspect of Synthetic Medical Images Deserves Our Focus?
Xing, X., Yang, N., Felder, F., Walsh, S. L. F., & Yang, G. (2023) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms58004.2023.00273 · Cited by 8
“In this study, we implemented StyleGAN2 as a representative model for the GAN family because StyleGAN2 methods have brought new standards for generative modeling regarding image quality [14].”
Method3D-Aware Multi-Class Image-to-Image Translation with NeRFs
Li, S., van de Weijer, J., Wang, Y., Khan, F. S., Liu, M., & Yang, J. 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/cvpr52729.2023.01217 · Cited by 8
Stable Attribute Group Editing for Reliable Few-Shot Image Generation
Ding, G., Han, X., Wang, S., Jin, X. Y., & Huang, Q. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3578670 · Cited by 8
“A S THE scale of models and the volume of visual data have increased, image generation models [1], [2], [3] have seen significant advancements in the quality, creativity, and controllability of the generated images.”
A Survey of Image Translation Based on Conditional Generative Adversarial Networks
Tu, H., Wang, W., Chen, J., Li, G., & Wu, F. Q. (2024) · Journal of Computer-Aided Design & Computer Graphics · doi:10.3724/sp.j.1089.2024.19807 · Cited by 8
Learning to See Through DazzlePreprint
Peng, X., Fleet, E. F., Watnik, A. T., & Swartzlander, G. A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.15919 · Cited by 8
“Disentangled representations [162], [163], [164] may improve the performance of GAN in the generation of images of a particular style (e.g., human face, outdoor scene, etc.), and its generalization to datasets containing versatile contents may require pretrained class embedding [165].”
BackgroundLaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and MambaPreprint
Fu, Y., Chen, C., & Yu, Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.02615 · Cited by 8
Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image DetectionPreprint
Qin, H., Chang, D., Gao, Y., Yu, B., Chen, L., & Ma, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.15217 · Cited by 8
“Generative Adversarial Networks (GANs) [20–24] and Diffusion models [25–29] are currently the predominant methods for generating forged images.”
Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings
Zhu, Y., Wang, X., Lathuilière, S., & Kalogeiton, V. S. (2025) · International Conference on Learning Representations · doi:10.48550/arxiv.2509.22925 · Cited by 8
Revisiting Diffusion Models: From Generative Pre-training to One-Step GenerationPreprint
Zheng, B., & Yang, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.09376 · Cited by 8
WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction
Zhuang, S., Guo, Y., Fu, C., Huang, Z., Tian, Z., Li, X., Wang, F., Zhang, Y., Li, C., & Wang, Y. (2025) · International Conference on Learning Representations · doi:10.48550/arxiv.2508.05599 · Cited by 8
Three-Body Scattering for Generative ModelingPreprint
Sun, P., Cheng, Z., Liu, D., Xie, J., Shang, X., & Lin, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.18198 · Cited by 8
“GANs (Goodfellow et al., 2014; Brock et al., 2018; Sauer et al., 2022; Kang et al., 2023) provide direct single-pass sampling but train the generator through a jointly learned discriminator or critic.”
Holistic Tokenizer for Autoregressive Image Generation
Zheng, A., Wang, H., Zhao, Y., Deng, W., Wang, T., Zhang, X., & Qi, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01571 · Cited by 7
LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation
Wang, J., Kang, N., Yao, L., Chen, M., Wu, C., Zhang, S., Xue, S., Liu, Y., Wu, T., Liu, X., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01491 · Cited by 8
Decentralized Deepfake Task Management Algorithm Based on Blockchain and Edge Computing
Yang, Y., Idris, N. B., Yu, D., Liu, C., & Wu, H. (2024) · IEEE Access · doi:10.1109/access.2024.3416458 · Cited by 7
“NVIDIA [5] has been early in this field.”
BackgroundDGL-GAN: discriminator-guided GAN compression
Tian, Y., Shen, L., Tian, X., Tao, D., Li, Z., Liu, W., & Chen, Y. (2024) · The Visual Computer · doi:10.1007/s00371-024-03682-y · Cited by 7
“…images, BigGAN [4] is the first to synthesize images on ImageNet with resolution 128x128 or 512x512, equipped with class conditional batch normalization, projection discriminator, etc. StyleGAN series [2, 3, 5, 15] are able to synthesize images with even higher resolution, e.g., 1024x1024 FFHQ.”
See Further When Clear: Curriculum Consistency Model
Liu, Y., Liu, B., Yi, Z., Hou, X., Song, G., Liu, Y., & You, H. (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/cvpr52734.2025.01687 · Cited by 7
Generation of Infrastructure Crack Images for Self-Supervision Training Based on Diffusion Model
Qin, S., Fang, Y., Li, Y., & Li, Z. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3597284 · Cited by 7
“Three popular GAN methods are also compared: BigGAN [56], StyleGAN2 [57], and SN-GAN [58].”
Lystbæk, M. S., Beliatis, M. J., & Giannakidis, A. (2025) · Journal of Building Engineering · doi:10.1016/j.jobe.2025.114211 · Cited by 7
On the Distributed Evaluation of Generative Models
Wang, Z., Farnia, F., Lin, Z., Shen, Y., & Yu, B. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00792 · Cited by 7
High-Resolution GAN Inversion for Degraded Images in Large Diverse Datasets
Wang, Y., Lin, C., Luo, D., Tai, Y. Y., Zhang, Z., & Xie, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i3.25371 · Cited by 7
GAMMA-FACE: GAussian Mixture Models Amend Diffusion Models for Bias Mitigation in Face Images
Pal, B., Kannan, A., Kathirvel, R. P., O’Toole, A. J., & Chellappa, R. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72855-6_27 · Cited by 7
Distill the Best, Ignore the Rest: Improving Dataset Distillation with Loss-Value-Based PruningPreprint
Moser, B. B., Raue, F., Nauen, T. C., Frolov, S., & Dengel, A. R. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.12115 · Cited by 7
“GLaD [3], one of the initial methods to leverage generative priors, employs a pre-trained StyleGAN-XL [21].”
Differentiable Solver Search for Fast Diffusion SamplingPreprint
Wang, S., Li, Z., zhang, Q., Song, T., Li, X., Ge, T., Zheng, B., & Wang, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.21114 · Cited by 8
“…Lipman et al., 2022; Wang et al., 2025) have recently emerged as highly promising solutions to learn the underlying data distribution in image generation, outperforming GAN-based models (Brock et al., 2018; Sauer et al., 2022) and Auto-Regressive models (Chang et al., 2022) by a significant margin.”
OAT-FM: Optimal Acceleration Transport for Improved Flow MatchingPreprint
Yue, A., Dong, A., & Xu, H. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.24936 · Cited by 7
“…whose endpoints are undesired (e.g., in the “Lion” generated by SiT-XL), OAT-FM significantly changes their directions, leading to new endpoints (Sauer et al., 2022) 2.30 4.02 265.1 0.78 0.53 Mask-GIT (Chang et al., 2022) 6.18 - 182.1 - - ADM-G/U (Dhariwal and Nichol, 2021) 3.94 6.14 215.8 0.83…”
InfluentialGuiding a Diffusion Transformer with the Internal Dynamics of ItselfPreprint
Zhou, X., li, Q., Hu, X., Chen, H., & Gu, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.24176 · Cited by 7
Label-Augmented Dataset Distillation
Kang, S., Lim, Y., & Shim, H. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00149 · Cited by 6
“To improve image representation, GLaD [3] and LatentDD [9] regularize the manifold of D based on GAN [27] and Diffusion Model [24].”
DefFiller: mask-conditioned generation with diffusion prior for saliency-based defect detection
Tai, Y., Huang, Z., Peng, T., & Zhang, Z. (2025) · The Visual Computer · doi:10.1007/s00371-025-04078-2 · Cited by 6
“Variants of GANs, such as Cycle-GAN [26] and StyleGAN [27], have been widely applied to various image generation tasks, including photograph car-toonization [28] and multi-stitch embroidery generation [29].”
Unveiling Deepfake and Fraudulent Content Generation in GPT Models and Countermeasures
Pentakota, S. L. B. (2025) · AVE Trends in Intelligent Computer Letters · doi:10.64091/aticl.2025.000095 · Cited by 6
Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
Hur, J., Lee, D.-J., Han, G., Choi, J., Jeon, Y., & Kim, J. (2024) · neural information processing systems · doi:10.52202/079017-4163 · Cited by 6
Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning
Zheng, H., Pu, N., Li, W., Long, T., Sebe, N., & Zhong, Z. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i16.38341 · Cited by 6
Latent Regularization in Generative Test Input Generation
Merabishvili, G., Weißl, O., & Stocco, A. (2026) · IEEE/ACM International Workshop on Deep Learning for Testing and Testing for Deep Learning (DeepTest) · doi:10.1145/3786154.3788585 · Cited by 6
TURBO: The Swiss Knife of Auto-Encoders
Quétant, G., Belousov, Y., Kinakh, V., & Voloshynovskiy, S. (2023) · Entropy · doi:10.3390/e25101471 · Cited by 6
“It can be pure random noise, as for the StyleGAN model [33], or also include additional information such as class labels, as for the BigGAN [34] and StyleGAN-XL [35] large-scale models, which nowadays still compete with other modern frameworks [36,37].”
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.