The DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.
Analyzing and Improving the Image Quality of StyleGAN
Open accessAbstract
The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and training methods to address them. In particular, we redesign the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images. In addition to improving image quality, this path length regularizer yields the additional benefit that the generator becomes significantly easier to invert. This makes it possible to reliably attribute a generated image to a particular network. We furthermore visualize how well the generator utilizes its output resolution, and identify a capacity problem, motivating us to train larger models for additional quality improvements. Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
“StyleGAN2 is also helping detect image deepfakes as it can see if the picture is generated by a network or not (Karras et al., 2020).”
From Audio deepfakes: A survey (2023) · cites this paper as Karras et al., 2020
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“StyleGAN2 (Karras et al. 2020) has exposed several typical artifacts of StyleGAN and has proposed changes in both model architecture and training methods to address them.”
From Countering Malicious DeepFakes: Survey, Battleground, and Horizon (2022) · cites this paper as Karras et al. 2020
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“LayerNorm) (Lei Ba et al., 2016) instead of Group Normalization (GroupNorm) (Wu and He, 2018), which prevents large magnitudes from appearing in specific regions of the latent space or reconstructed outputs (Karras et al., 2020; Sadat et al., 2024).”
From Cosmos World Foundation Model Platform for Physical AI (2025) · cites this paper as Karras et al., 2020
Experimental — accuracy not yet measured
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Book Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066
The Unreasonable Effectiveness of Deep Features as a Perceptual MetricPreprint
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.48550/arxiv.1801.03924 · Cited by 21,362
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
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
(2010) · Cited by 14,134
A 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
Self-citationGANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365
Improved training of Wasserstein GANs
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. (2017) · arXiv · doi:10.48550/arxiv.1704.00028 · Cited by 6,800
Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization
Huang, X., & Belongie, S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.167 · Cited by 5,076
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2017) · arXiv · doi:10.48550/arxiv.1710.10196 · Cited by 4,727
Self-citationDeep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Brock, A., Donahue, J., & Simonyan, K. (2018) · arXiv · doi:10.48550/arxiv.1809.11096 · Cited by 3,717
Spectral Normalization for Generative Adversarial Networks
Miyato, T., Kataoka, T., Koyama, M., & Yoshida, Y. (2018) · arXiv · doi:10.48550/arxiv.1802.05957 · Cited by 3,438
Self-Attention Generative Adversarial Networks
Zhang, H., Goodfellow, I., Metaxas, D., & Odena, A. (2018) · arXiv · doi:10.48550/arxiv.1805.08318 · Cited by 3,353
StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., & Metaxas, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.629 · Cited by 3,021
LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the LoopPreprint
Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., & Xiao, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.03365 · Cited by 2,318
Deep Generative Image Models using a Laplacian Pyramid of Adversarial NetworksPreprint
Denton, E., Chintala, S., Szlam, A. D., & Fergus, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.05751 · Cited by 1,789
Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural NetworksPreprint
Salimans, T., & Kingma, D. P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.07868 · Cited by 1,551
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F. A., & Brendel, W. (2018) · arXiv · doi:10.48550/arxiv.1811.12231 · Cited by 1,490 · cited 2×
“Both FID and P&R are based on classifier networks that have recently been shown to focus on textures rather than shapes [10], and consequently, the metrics do not accurately capture all aspects of image quality.”
BackgroundStackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X., & Metaxas, D. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2856256 · Cited by 1,267
The importance of shape in early lexical learning
Landau, B., Smith, L. B., & Jones, S. S. (1988) · Cognitive Development · doi:10.1016/0885-2014(88)90014-7 · Cited by 1,174
A Learned Representation For Artistic StylePreprint
Dumoulin, V., Shlens, J., & Kudlur, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.07629 · Cited by 1,114
Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?
Abdal, R., Qin, Y., & Wonka, P. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00453 · Cited by 1,085
Interpreting the Latent Space of GANs for Semantic Face Editing
Shen, Y., Gu, J., Tang, X., & Zhou, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00926 · Cited by 1,063
Which Training Methods for GANs do actually Converge?Preprint
Mescheder, L., Geiger, A., & Nowozin, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.04406 · Cited by 1,029
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet ClassificationPreprint
He, K., Zhang, X., Ren, S., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.01852 · Cited by 1,000
Williams, L. R. (1983) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/800059.801126 · Cited by 737
Detecting and Simulating Artifacts in GAN Fake Images
Zhang, X., Karaman, S., & Chang, S.-F. (2019) · 2019 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs47025.2019.9035107 · Cited by 567
Generative Adversarial Networks
Salvaris, M., Dean, D., & Tok, W. H. (2018) · Apress eBooks · doi:10.1007/978-1-4842-3679-6_8 · Cited by 411
Improved Precision and Recall Metric for Assessing Generative Models
Kynkäänniemi, T., Karras, T., Laine, S., Lehtinen, J., & Aila, T. (2019) · arXiv · doi:10.48550/arxiv.1904.06991 · Cited by 379
Self-citationAssessing Generative Models via Precision and RecallPreprint
Sajjadi, M. S. M., Bachem, O., Lučić, M., Bousquet, O., & Gelly, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.00035 · Cited by 360
Williams, L. R. (1983) · ACM SIGGRAPH Computer Graphics · doi:10.1145/964967.801126 · Cited by 310
Exploring the structure of a real-time, arbitrary neural artistic stylization network
Ghiasi, G., Lee, H., Kudlur, M., Dumoulin, V., & Shlens, J. (2017) · Procedings of the British Machine Vision Conference 2017 · doi:10.5244/c.31.114 · Cited by 306
MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks
Karnewar, A., & Wang, O. (2020) · 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/cvpr42600.2020.00782 · Cited by 265
Dumoulin, V., Perez, E., Schucher, N., Strub, F., de Vries, H., Courville, A. C., & Bengio, Y. (2018) · Distill · doi:10.23915/distill.00011 · Cited by 192
Equilibrated adaptive learning rates for non-convex optimizationPreprint
Dauphin, Y., de Vries, H., & Bengio, Y. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.04390 · Cited by 172
Is Generator Conditioning Causally Related to GAN Performance?Preprint
Odena, A., Buckman, J., Olsson, C., Brown, T. B., Olah, C., Raffel, C., & Goodfellow, I. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.08768 · Cited by 90
Interpreting the Latent Space of GANs for Semantic Face EditingPreprint
Shen, Y., Gu, J., Tang, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.10786 · Cited by 74
On the Effects of Batch and Weight Normalization in Generative Adversarial NetworksPreprint
Xiang, S., & Li, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.03971 · Cited by 65
CNN-generated images are surprisingly easy to spot... for nowPreprint
Wang, S.-Y., Wang, O., Zhang, R., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.11035 · Cited by 44
Detecting and Simulating Artifacts in GAN Fake ImagesPreprint
Zhang, X., Karaman, S., & Chang, S.-F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.06515 · Cited by 39
Attributing Fake Images to GANs: Learning and Analyzing GAN FingerprintsPreprint
Yu, N., Davis, L. S., & Fritz, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.08180 · Cited by 38
FakeSpotter: A Simple Baseline for Spotting AI-Synthesized Fake Faces
Wang, R., Ma, L., Juefei-Xu, F., Xie, X., Wang, J., & Liu, Y. (2019) · Cited by 36
Attributing Fake Images to GANs: Analyzing Fingerprints in Generated Images.Preprint
Yu, N., Davis, L. S., & Fritz, M. (2018) · arXiv (Cornell University) · Cited by 33
Arbitrary Style Transfer in Real-time with Adaptive Instance NormalizationPreprint
Huang, X. C., & Belongie, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.06868 · Cited by 32
FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake FacesPreprint
Wang, R., Juefei-Xu, F., Ma, L., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.06122 · Cited by 32
Source Generator Attribution via InversionPreprint
Albright, M., & McCloskey, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.02259 · Cited by 30
Can Forensic Detectors Identify GAN Generated Images?
Li, H.-D., Chen, H., Li, B., & Tan, S. (2018) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference · doi:10.23919/apsipa.2018.8659461 · Cited by 24
Style Generator Inversion for Image Enhancement and AnimationPreprint
Gabbay, A., & Hoshen, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.11880 · Cited by 20
Research works printed but not linked: 3
- nikitko, 2019, StyleGAN - Encoder for official Ten-sorFlow implementation
- bergstrom, 0, Which face is real?
- zhang, 0, Making convolutional networks shift-invariant again, Proc ICML
Cited by
Sorted by citations
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712
Diffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Score-Based Generative Modeling through Stochastic Differential Equations
Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2020) · arXiv · doi:10.48550/arxiv.2011.13456 · Cited by 1,953
Metadata
- Authors
- Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T.
- Affiliations
- Nvidia (United Kingdom) (GB)
- Aalto University (FI)
- Venue
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 8107-8116
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2995327724
- Semantic Scholar
- 14fdc18d9c164e5b0d6d946b3238c04e81921358
- Cited by
- 6,332
- References
- 55
- Citations by year
- 2026: 463 · 2025: 1070 · 2024: 1389 · 2023: 1362 · 2022: 1009 · 2021: 792 · 2020: 243
- FWCI
- 262.37
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- TIB Data Manager
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- StyleGAN, image quality, unconditional image generation, model capacity
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
