Image Super-Resolution Via Iterative Refinement
Open accessThe DOI matches its Crossref record; 81 of the 85 references it cites were found in a registry or an index.
Abstract
We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3 adapts denoising diffusion probabilistic models (Ho et al. 2020), (Sohl-Dickstein et al. 2015) to image-to-image translation, and performs super-resolution through a stochastic iterative denoising process. Output images are initialized with pure Gaussian noise and iteratively refined using a U-Net architecture that is trained on denoising at various noise levels, conditioned on a low-resolution input image. SR3 exhibits strong performance on super-resolution tasks at different magnification factors, on faces and natural images. We conduct human evaluation on a standard 8× face super-resolution task on CelebA-HQ for which SR3 achieves a fool rate close to 50%, suggesting photo-realistic outputs, while GAN baselines do not exceed a fool rate of 34%. We evaluate SR3 on a 4× super-resolution task on ImageNet, where SR3 outperforms baselines in human evaluation and classification accuracy of a ResNet-50 classifier trained on high-resolution images. We further show the effectiveness of SR3 in cascaded image generation, where a generative model is chained with super-resolution models to synthesize high-resolution images with competitive FID scores on the class-conditional 256×256 ImageNet generation challenge.
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
Figures

































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
“Both the SR3 and CDM directly apply the diffusion process to input images, which leads to larger evaluation steps.”
From Diffusion Models: A Comprehensive Survey of Methods and Applications (2024) · cites this paper as [200]
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
“Low-light face videos suffer from severe noise and detail loss, limiting their use in surveillance and photography applications.”
From Temporally consistent low-light face video enhancement via video-to-video conditional diffusion (2026) · cites this paper as [5]
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
“This greatly improves FID on ImageNet 256×256, but does not reach the same performance as state-of-the-art models like BigGAN-deep [43, 53], as seen in Table 5.”
From Diffusion Models Beat GANs on Image Synthesis (2021) · cites this paper as [53]
Experimental — accuracy not yet measuredIn the citing paper
“Super-Resolution via Repeated Refinement (SR3) [200] uses DDPM to enable conditional image generation.”
From Diffusion Models: A Comprehensive Survey of Methods and Applications (2024) · cites this paper as [200]
In the citing paper
“SR3 conducts super-resolution through a stochastic, iterative denoising process.”
From Diffusion Models: A Comprehensive Survey of Methods and Applications (2024) · cites this paper as [200]
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 · cited 1×
“Then, we report classification accuracy of a pre-trained ResNet50 [65] model.”
MethodVaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
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
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · cited 10×
“Table 2 shows the PSNR, SSIM [63] and Consistency scores for 16 16 !”
BackgroundInfluentialImageNet 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 · cited 2×
“on ImageNet 1K [62] and use the dev split for evaluation.”
BackgroundMethodAuto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067 · cited 2×
“VAEs [7], [46] offer fast sampling, but tend to underperform GANs”
BackgroundGenerative adversarial networks
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020) · Communications of the ACM · doi:10.1145/3422622 · Cited by 18,384
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.19 · Cited by 12,696
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 1×
“Autoregressive models [5], [6], variational autoencoders (VAEs) [7], [8], Normalizing Flows (NFs) [9], [10], and GANs [11], [12], [13] have shown convincing image generation results and benefited conditional tasks such as image super-resolution [14], [15], [16], [17], [18].”
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 2×
“We follow previous work [17], training face super-resolution models on Flickr-Faces-HQ (FFHQ) [61] and evaluating on CelebA-HQ [12].”
MethodImage Super-Resolution Using Deep Convolutional Networks
Dong, C., Loy, C. C., He, K., & Tang, X. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2439281 · Cited by 10,105
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712 · cited 18×
“The SR3 architecture is similar to the U-Net in DDPM [1], with self-attention and modifications adapted from [40]; i.e., we replace the original DDPM residual blocks with residual blocks from BigGAN [41], and we re-scale skip connections by 1ffiffi 2 p .”
BackgroundMethodInfluentialSelf-citationAccurate Image Super-Resolution Using Very Deep Convolutional Networks
Kim, J., Lee, J. K., & Lee, K. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.182 · Cited by 7,870 · cited 2×
“sion based and trained with an MSE loss [49], [52], [54], [55], [56].”
BackgroundImproved 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 · cited 2×
“Nevertheless, the inner-outer loop optimization often requires tricks to stabilize training [2, 15], and conditional tasks like super-resolution usually require an auxiliary consistencybased loss to avoid mode collapse [25].”
BackgroundImage Super-Resolution Using Very Deep Residual Channel Attention Networks
Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., & Fu, Y. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_18 · Cited by 5,708
Learning a Deep Convolutional Network for Image Super-Resolution
Dong, C., Loy, C. C., He, K., & Tang, X. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10593-2_13 · Cited by 5,494 · cited 2×
“sion based and trained with an MSE loss [49], [52], [54], [55], [56].”
WaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911 · cited 1×
“Autoregressive models [5], [6], variational autoencoders (VAEs) [7], [8], Normalizing Flows (NFs) [9], [10], and GANs [11], [12], [13] have shown convincing image generation results and benefited conditional tasks such as image super-resolution [14], [15], [16], [17], [18].”
BackgroundESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Qiao, Y., & Loy, C. C. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-11021-5_5 · Cited by 4,731
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 · cited 5×
“GAN-based super-resolution methods have also found considerable success [12], [16], [17], [30], [31], [32], [59].”
BackgroundMethodInfluentialGenerative Adversarial Networks
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1406.2661 · Cited by 4,477
Accelerating the Super-Resolution Convolutional Neural Network
Dong, C., Loy, C. C., & Tang, X. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_25 · Cited by 3,786
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 · cited 6×
“The SR3 architecture is similar to the U-Net in DDPM [1], with self-attention and modifications adapted from [40]; i.e., we replace the original DDPM residual blocks with residual blocks from BigGAN [41], and we re-scale skip connections by 1ffiffi 2 p .”
MethodInfluentialZhang, R., Isola, P., & Efros, A. A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_40 · Cited by 3,178
Deeply-Recursive Convolutional Network for Image Super-Resolution
Kim, J., Lee, J. K., & Lee, K. M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.181 · Cited by 3,025 · cited 1×
“Numerous super-resolution methods have been proposed [16], [30], [31], [32], [49], [50], [51], [52], [53].”
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., & Ganguli, S. (2015) · arXiv · doi:10.48550/arxiv.1503.03585 · Cited by 2,637 · cited 19×
“If the noise variance of the forward process steps are set as small as possible, i.e., a1:T 1, the optimal reverse process pðyt 1jyt; xÞwill be approximately Gaussian [23].”
BackgroundMethodInfluentialDenoising Diffusion Implicit Models
Song, J., Meng, C., & Ermon, S. (2020) · arXiv · doi:10.48550/arxiv.2010.02502 · Cited by 2,507
Film: Visual reasoning with a general conditioning layer
Perez, E., Strub, F., De Vries, H., Dumoulin, V., & Courville, A. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11671 · Cited by 2,490
Image Super-Resolution via Deep Recursive Residual Network
Tai, Y., Yang, J., & Liu, X. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.298 · Cited by 2,415 · cited 1×
“Numerous super-resolution methods have been proposed [16], [30], [31], [32], [49], [50], [51], [52], [53].”
Stochastic Backpropagation and Approximate Inference in Deep Generative Models
Rezende, D. J., Mohamed, S., & Wierstra, D. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1401.4082 · Cited by 2,405
Arjovsky, M., Chintala, S., & Bottou, L. (2017) · arXiv · doi:10.48550/arxiv.1701.07875 · Cited by 2,225
Density estimation using Real NVP
Dinh, L., Sohl-Dickstein, J., & Bengio, S. (2016) · arXiv · Cited by 2,067 · cited 2×
“Normalizing flows [9], [10], [45] improve on sampling speed”
BackgroundScore-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 · cited 3×
“The SR3 architecture is similar to the U-Net in DDPM [1], with self-attention and modifications adapted from [40]; i.”
BackgroundMethodConditional Image Generation with PixelCNN Decoders
van den Oord, A., Kalchbrenner, N., Vinyals, O., Espeholt, L., Graves, A., & Kavukcuoglu, K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.05328 · Cited by 1,833 · cited 1×
“Autoregressive models have been used successfully for super-resolution and cascaded up-sampling [15], [18], [57], [58].”
MethodPalette: Image-to-Image Diffusion Models
Saharia, C., Chan, W., Chang, H., Lee, C., Ho, J., Salimans, T., Fleet, D., & Norouzi, M. (2022) · Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings · doi:10.1145/3528233.3530757 · Cited by 1,717 · cited 1×
“However, subsequent work shows that L2 tends to generate greater diversity in SR3 outputs [34].”
BackgroundSelf-citationConditional Image Generation with PixelCNN DecodersPreprint
van den Oord, A., Kalchbrenner, N., Vinyals, O., et al. (2016) · arXiv (Cornell University) · Cited by 1,586
Improved Denoising Diffusion Probabilistic Models
Nichol, A., & Dhariwal, P. (2021) · arXiv · doi:10.48550/arxiv.2102.09672 · Cited by 1,550
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
Denton, E., Chintala, S., Szlam, A. D., & Fergus, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.05751 · Cited by 1,541
Generative Modeling by Estimating Gradients of the Data Distribution
Song, Y., & Ermon, S. (2019) · arXiv · doi:10.48550/arxiv.1907.05600 · Cited by 1,453 · cited 3×
“Thus, the denoising model is aware of the level of noise through conditioning on g, similar to [24], [33].”
BackgroundPixel Recurrent Neural Networks
van den Oord, A., Kalchbrenner, N., & Kavukcuoglu, K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1601.06759 · Cited by 1,437 · cited 1×
“Autoregressive models (ARs) [43], [44] can model exact data log likelihood, capturing rich distributions.”
BackgroundGenerating Images with Perceptual Similarity Metrics based on Deep NetworksPreprint
Dosovitskiy, A., & Brox, T. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1602.02644 · Cited by 1,276 · cited 1×
“[26] observed that these conventional automated evaluation measures do not correlate well with human perception when”
BackgroundVariational Inference with Normalizing Flows
Rezende, D. J., & Mohamed, S. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.05770 · Cited by 1,253 · cited 1×
“Normalizing flows [9], [10], [45] improve on sampling speed”
BackgroundParmar, N., Vaswani, A., Uszkoreit, J., Kaiser, Ł., Shazeer, N., Ku, A., & Tran, D. (2018) · arXiv · doi:10.48550/arxiv.1802.05751 · Cited by 1,085 · cited 2×
“Autoregressive models have been used successfully for super-resolution and cascaded up-sampling [15], [18], [57], [58].”
BackgroundMethodEnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
Sajjadi, M. S. M., Scholkopf, B., & Hirsch, M. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.481 · Cited by 1,058 · cited 8×
“Following [31], [64] we apply 4 super-resolution models to 56 56 center crops from the validation set of ImageNet.”
BackgroundMethodResultInfluentialA Connection Between Score Matching and Denoising Autoencoders
Vincent, P. (2011) · Neural Computation · doi:10.1162/neco_a_00142 · Cited by 1,011 · cited 2×
“Score matching on noisy data, called denoising score matching [36], is equivalent to training a denoising autoencoder, and to DDPMs [1].”
MethodGlow: Generative Flow with Invertible 1x1 Convolutions
Kingma, D. P., & Dhariwal, P. (2018) · arXiv · Cited by 825 · cited 2×
“Normalizing flows [9], [10], [45] improve on sampling speed”
BackgroundDeep Networks for Image Super-Resolution with Sparse Prior
Wang, Z., Liu, D., Yang, J., Han, W., & Huang, T. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.50 · Cited by 784 · cited 1×
“sion based and trained with an MSE loss [49], [52], [54], [55], [56].”
WaveGrad: Estimating Gradients for Waveform GenerationPreprint
Chen, N., Zhang, Y., Zen, H., Weiss, R. J., Norouzi, M., & Chan, W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.00713 · Cited by 758 · cited 6×
“We also emphasize that this search is inexpensive as it does not requiremodel retraining [33].”
BackgroundMethodInfluentialSelf-citation(2005) · doi:10.5555/1046920.1088696 · Cited by 756
Generating diverse high-fidelity images with vq-vae-2
Razavi, A., Oord, A. V. D., & Vinyals, O. (2019) · arXiv · doi:10.48550/arxiv.1906.00446 · Cited by 709 · cited 2×
“Our 2-stage model improves on VQVAE-2 [71], is comparable to deep BigGANs [41] at truncation factor of 1.5 but underperforms them a truncation factor of 1.0.”
MethodInfluentialSalimans, T., Karpathy, A., Chen, X., & Kingma, D. P. (2017) · arXiv · doi:10.48550/arxiv.1701.05517 · Cited by 584 · cited 1×
“Autoregressive models (ARs) [43], [44] can model exact data log likelihood, capturing rich distributions.”
BackgroundSelf-citationFSRNet: End-to-End Learning Face Super-Resolution with Facial Priors
Chen, Y., Tai, Y., Liu, X., Shen, C., & Yang, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00264 · Cited by 581
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
Menon, S., Damian, A., Hu, S., Ravi, N., & Rudin, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00251 · Cited by 532
Cascaded Diffusion Models for High Fidelity Image Generation
Ho, J., Saharia, C., Chan, W., Fleet, D. J., Norouzi, M., & Salimans, T. (2021) · arXiv · doi:10.48550/arxiv.2106.15282 · Cited by 514 · cited 1×
“models trained directly, which has been confirmed in more recent work [72].”
ResultSelf-citationImproved Techniques for Training Score-Based Generative Models
Song, Y., & Ermon, S. (2020) · arXiv · doi:10.48550/arxiv.2006.09011 · Cited by 482 · cited 1×
“Song and Ermon [39] advocate the use of a Multi-scale Guassian mixture as the target density, where each data point is perturbed with different amounts of Gaussian noise, so that Langevin dynamics starting from pure noise can still yield reasonable samples.”
BackgroundUnrolled Generative Adversarial Networks
Metz, L., Poole, B., Pfau, D., & Sohl‐Dickstein, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.02163 · Cited by 382 · cited 1×
“instability and mode collapse [19], [20], [21], [22].”
BackgroundNVAE: A Deep Hierarchical Variational Autoencoder
Vahdat, A., & Kautz, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.03898 · Cited by 350 · cited 1×
“Autoregressive models [5], [6], variational autoencoders (VAEs) [7], [8], Normalizing Flows (NFs) [9], [10], and GANs [11], [12], [13] have shown convincing image generation results and benefited conditional tasks such as image super-resolution [14], [15], [16], [17], [18].”
BackgroundSRFlow: Learning the Super-Resolution Space with Normalizing Flow
Lugmayr, A., Danelljan, M., Van Gool, L., & Timofte, R. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58558-7_42 · Cited by 347
Gotta Go Fast When Generating Data with Score-Based ModelsPreprint
Jolicoeur‐Martineau, A., Li, K., Piché-Taillefer, R., Kachman, T., & Mitliagkas, I. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.14080 · Cited by 301
Comparison of Four Subjective Methods for Image Quality Assessment
Mantiuk, R. K., Tomaszewska, A., & Mantiuk, R. (2012) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2012.03188.x · Cited by 288 · cited 1×
“While mean opinion score (MOS) is commonly used to measure image quality in this context, forced choice pairwise comparison has been found to be a more reliable method for such subjective quality assessments [69].”
MethodProgressive Distillation for Fast Sampling of Diffusion Models
Salimans, T., & Ho, J. (2022) · arXiv · doi:10.48550/arxiv.2202.00512 · Cited by 287
Self-citationDensely Residual Laplacian Super-Resolution
Anwar, S., & Barnes, N. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3021088 · Cited by 281
Image Super-Resolution via Progressive Cascading Residual Network
Ahn, N., Kang, B., & Sohn, K.-A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00123 · Cited by 277 · cited 3×
“sion based and trained with an MSE loss [49], [52], [54], [55], [56].”
BackgroundPixel Recursive Super Resolution
Dahl, R., Norouzi, M., & Shlens, J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.581 · Cited by 246
Self-citationLearning Gradient Fields for Shape Generation
Cai, R., Yang, G., Averbuch-Elor, H., Hao, Z., Belongie, S., Snavely, N., & Hariharan, B. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58580-8_22 · Cited by 225
Blind Face Restoration via Deep Multi-scale Component Dictionaries
Li, X., Chen, C., Zhou, S., Lin, X., Zuo, W., & Zhang, L. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58545-7_23 · Cited by 196
Classification Accuracy Score for Conditional Generative ModelsPreprint
Ravuri, S. V., & Vinyals, O. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.10887 · Cited by 179 · cited 1×
“instability and mode collapse [19], [20], [21], [22].”
BackgroundPalette: Image-to-Image Diffusion ModelsPreprint
Saharia, C., Chan, W., Chang, H., Lee, C. A., Ho, J., Salimans, T., Fleet, D. J., & Norouzi, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.05826 · Cited by 175 · cited 1×
“However, subsequent work shows that L2 tends to generate greater diversity in SR3 outputs [34].”
BackgroundSelf-citationHiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
Yang, L., Wang, S., Ma, S., Gao, W., Liu, C., Wang, P., & Ren, P. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413965 · Cited by 171 · cited 1×
“GAN-based super-resolution methods have also found considerable success [12], [16], [17], [30], [31], [32], [59].”
BackgroundLearning to Efficiently Sample from Diffusion Probabilistic ModelsPreprint
Watson, D., Ho, J., Norouzi, M., & Chan, W. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.03802 · Cited by 170 · cited 1×
“That said, recent and concurrent work proposes alternative approaches that can result in higher quality fast samplers for diffusionmodels [73], [74], [75], [76].”
BackgroundSelf-citationGenerating High Fidelity Images with Subscale Pixel Networks and Multidimensional UpscalingPreprint
Menick, J., & Kalchbrenner, N. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.01608 · Cited by 132 · cited 1×
“Autoregressive models have been used successfully for super-resolution and cascaded up-sampling [15], [18], [57], [58].”
MethodLeast Squares Estimation Without Priors or Supervision
Raphan, M., & Simoncelli, E. P. (2010) · Neural Computation · doi:10.1162/neco_a_00076 · Cited by 116 · cited 1×
“Our approach is also linked to denoising score matching [35], [36], [37], [38] for training unnormalized energy”
MethodSolving Linear Inverse Problems Using the Prior Implicit in a DenoiserPreprint
Kadkhodaie, Z., & Simoncelli, E. P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.13640 · Cited by 103
Deep Energy Estimator NetworksPreprint
Saremi, S., Mehrjou, A., Schölkopf, B., & Hyvärinen, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.08306 · Cited by 71 · cited 1×
“Our approach is also linked to denoising score matching [35], [36], [37], [38] for training unnormalized energy”
MethodScore-Based Generative Modeling through Stochastic Differential Equations
Song, Y. S., Sohl‐Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2021) · International Conference on Learning Representations · Cited by 71
Deep unsupervised learning using nonequilibrium thermodynamics
Sohl‐Dickstein, J. (2024) · International Conference on Machine Learning · doi:10.57702/qrfwyszh · Cited by 61
PSyCo: Manifold Span Reduction for Super Resolution
Pérez-Pellitero, E., Salvador, J., Ruiz‐Hidalgo, J., & Rosenhahn, B. (2016) · 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/cvpr.2016.203 · Cited by 57
Denoising diffusion probabilistic models
Ho, J. (2024) · TIB Data Manager · doi:10.57702/q2z1tfp2 · Cited by 51
Self-citationWavelet Flow: Fast Training of High Resolution Normalizing FlowsPreprint
Yu, J. J., Derpanis, K. G., & Brubaker, M. A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.13821 · Cited by 30 · cited 1×
“with a multi-scale approach [32], [60].”
Creating High Resolution Images with a Latent Adversarial GeneratorPreprint
Berthelot, D., Milanfar, P., & Goodfellow, I. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.02365 · Cited by 17
Cited by
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
“In the context of image synthesis, however, combining the generative power of DMs with other types of conditionings beyond class-labels [15] or blurred variants of the input image [70] is so far an under-explored area of research.”
InfluentialDiffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362
“In this section, we demonstrate that we can achieve results better than StyleGAN2 and BigGAN-deep with the same or lower compute budget.”
BackgroundMethodInfluentialPhotorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E., Ghasemipour, S. K. S., Ayan, B. K., Mahdavi, S. S., Lopes, R. G., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.11487 · Cited by 2,528
“Diffusion models have seen wide success in image generation [28, 42, 62, 16, 29, 61], outperforming GANs in fidelity and diversity, without training instability and mode collapse issues [6, 16, 29].”
BackgroundSelf-citationHierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511
“For the first upsampling stage, we use gaussian blur [43], and for the second, we use a more diverse BSR degradation [42,”
MethodDreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2022) · arXiv · doi:10.48550/arxiv.2208.12242 · Cited by 2,442
“[62] Chitwan Saharia, Jonathan Ho, William Chan, Tim Salimans, David J Fleet, and Mohammad Norouzi.”
Background
Metadata
- Authors
- Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D. J., & Norouzi, M.
- Affiliations
- Google (United States) (US)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2022
- Volume
- 45
- Issue
- 4
- Pages
- 1-14
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W3155072588
- Cited by
- 1,829
- References
- 85
- Citations by year
- 2026: 234 · 2025: 580 · 2024: 662 · 2023: 301 · 2022: 40
- FWCI
- 129.48
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- image super-resolution, iterative refinement, denoising diffusion probabilistic models, image-to-image translation, U-Net, face super-resolution, high-resolution image generation, human evaluation, image classification accuracy
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.