Blau and Michaeli, “The Perception-Distortion Tradeoff” (CVPR 2018)
Optional · paper guide 1 of 5 for DLCV 09B · Generative Image Restoration: Sampling a Plausible Answer. Citation numbers refer to the reference list at the bottom of this page.
Navigate: this page and this track: Navigate: this page and this track
On this page
- Blau and Michaeli, “The Perception-Distortion Tradeoff” (CVPR 2018)
- Chung et al., “Diffusion Posterior Sampling for General Noisy Inverse Problems” (ICLR 2023)
- DDNM: preserve measured components and generate the null space
- BlindDPS: infer an image and its degradation together
- Li et al., “Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey” (IJCV 2025)
Deep Learning for Computer Vision
Challenge
By 2017, super-resolution methods trained with adversarial losses produced images that people preferred, yet they scored worse in PSNR and SSIM than MSE-trained networks. Was this a flaw of the metrics, or something unavoidable?

Figure source: [1], arXiv:1711.06077v4, PDF page 1. Original PDF.
Method
Define perceptual quality as a property of the output distribution, the divergence between the distribution of restored images and that of real images (which a perfect discriminator would detect), and study the best possible distortion for each level of perceptual quality, over all possible estimators [1].
Results
The perception–distortion function is monotone, and convex for convex divergences, so the trade-off is a mathematical property of the problem, not of a particular metric or network, and it holds for every distortion measure. For squared error, perfect perceptual quality costs at most twice the minimum MSE, reached by posterior sampling (in the extended arXiv version). GAN training with a distortion term and an adversarial term is a principled way to approach the bound. The paper then plots many super-resolution methods of the time on the plane, using no-reference metrics as proxies for perceptual quality.
Reading the evidence
Start with the definitions and Theorem 2 (the trade-off), then the factor-of-two result and its proof in the appendix, which is the argument in our Supplementary notes. When reading the experimental plots, check: (a) that the “perceptual quality” axis there is a no-reference metric (a proxy), not the divergence of the theory; (b) that the bound is drawn qualitatively, since it cannot be computed for real images; (c) which color channel and evaluation protocol were used for PSNR.
Problems
The theory is about distributions and expectations; it says nothing about which particular details an estimator invents, so it does not measure hallucination. The bound is not computable for natural images, and the factor of two is an upper bound, not a prediction.
Conclusion
It is the theory behind every section of this chapter: why MSE networks blur, why generative methods lose PSNR, and why a method should be described by a point on a plane rather than a single score.
References
- Y. Blau and T. Michaeli, “The Perception-Distortion Tradeoff,” in Proc. IEEE/CVF CVPR, 2018, pp. 6228–6237 (extended version on arXiv). doi · arXiv
- C. Ledig, L. Theis, F. Huszár, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang and W. Shi, “Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network,” in Proc. IEEE CVPR, 2017, pp. 105–114. doi · arXiv
- J. Johnson, A. Alahi and L. Fei-Fei, “Perceptual Losses for Real-Time Style Transfer and Super-Resolution,” in Proc. ECCV, 2016, pp. 694–711. doi · arXiv
- X. Wang, K. Yu, S. Wu, J. Gu, Y. Liu, C. Dong, Y. Qiao and C. C. Loy, “ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks,” in Proc. ECCV Workshops, 2018 (LNCS, 2019), pp. 63–79. doi · arXiv
- X. Wang, L. Xie, C. Dong and Y. Shan, “Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data,” in Proc. IEEE/CVF ICCV Workshops, 2021, pp. 1905–1914. doi · arXiv
- T. Karras, S. Laine and T. Aila, “A Style-Based Generator Architecture for Generative Adversarial Networks,” in Proc. IEEE/CVF CVPR, 2019, pp. 4396–4405. doi · arXiv
- S. Menon, A. Damian, S. Hu, N. Ravi and C. Rudin, “PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models,” in Proc. IEEE/CVF CVPR, 2020, pp. 2434–2442. doi · arXiv
- K. C. K. Chan, X. Wang, X. Xu, J. Gu and C. C. Loy, “GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution,” in Proc. IEEE/CVF CVPR, 2021, pp. 14240–14249. doi · arXiv
- X. Wang, Y. Li, H. Zhang and Y. Shan, “Towards Real-World Blind Face Restoration with Generative Facial Prior,” in Proc. IEEE/CVF CVPR, 2021, pp. 9164–9174. doi · arXiv
- S. Zhou, K. C. K. Chan, C. Li and C. C. Loy, “Towards Robust Blind Face Restoration with Codebook Lookup Transformer,” in Proc. NeurIPS, vol. 35, 2022, pp. 30599–30611. doi · arXiv
- J. Ho, A. Jain and P. Abbeel, “Denoising Diffusion Probabilistic Models,” in Proc. NeurIPS, 2020. proceedings · arXiv
- Y. Song, J. Sohl-Dickstein, D. P. Kingma, A. Kumar, S. Ermon and B. Poole, “Score-Based Generative Modeling through Stochastic Differential Equations,” in Proc. ICLR, 2021. arXiv
- B. Efron, “Tweedie’s Formula and Selection Bias,” Journal of the American Statistical Association, vol. 106, no. 496, pp. 1602–1614, 2011. doi
- C. Saharia, J. Ho, W. Chan, T. Salimans, D. J. Fleet and M. Norouzi, “Image Super-Resolution via Iterative Refinement,” IEEE TPAMI, 2022 (early access). doi · arXiv
- C. Saharia, W. Chan, H. Chang, C. Lee, J. Ho, T. Salimans, D. Fleet and M. Norouzi, “Palette: Image-to-Image Diffusion Models,” in Proc. ACM SIGGRAPH Conference, 2022, pp. 1–10. doi · arXiv
- Z. Yue, J. Wang and C. C. Loy, “ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting,” in Proc. NeurIPS, vol. 36, 2023, pp. 13294–13307. doi · arXiv
- H. Chung, J. Kim, M. T. McCann, M. L. Klasky and J. C. Ye, “Diffusion Posterior Sampling for General Noisy Inverse Problems,” in Proc. ICLR, 2023. arXiv
- B. Kawar, M. Elad, S. Ermon and J. Song, “Denoising Diffusion Restoration Models,” in Proc. NeurIPS, vol. 35, 2022, pp. 23593–23606. doi · arXiv
- Y. Wang, J. Yu and J. Zhang, “Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model,” in Proc. ICLR, 2023. arXiv
- J. Song, A. Vahdat, M. Mardani and J. Kautz, “Pseudoinverse-Guided Diffusion Models for Inverse Problems,” in Proc. ICLR, 2023. ICLR page
- Y. Zhu, K. Zhang, J. Liang, J. Cao, B. Wen, R. Timofte and L. Van Gool, “Denoising Diffusion Models for Plug-and-Play Image Restoration,” in Proc. IEEE/CVF CVPR Workshops, 2023, pp. 1219–1229. doi · arXiv
- R. Rombach, A. Blattmann, D. Lorenz, P. Esser and B. Ommer, “High-Resolution Image Synthesis with Latent Diffusion Models,” in Proc. IEEE/CVF CVPR, 2022, pp. 10674–10685. doi · arXiv
- L. Zhang, A. Rao and M. Agrawala, “Adding Conditional Control to Text-to-Image Diffusion Models,” in Proc. IEEE/CVF ICCV, 2023, pp. 3813–3824. doi · arXiv
- J. Wang, Z. Yue, S. Zhou, K. C. K. Chan and C. C. Loy, “Exploiting Diffusion Prior for Real-World Image Super-Resolution,” International Journal of Computer Vision, vol. 132, no. 12, pp. 5929–5949, 2024. doi · arXiv
- X. Lin, J. He, Z. Chen, Z. Lyu, B. Dai, F. Yu, Y. Qiao, W. Ouyang and C. Dong, “DiffBIR: Toward Blind Image Restoration with Generative Diffusion Prior,” in Proc. ECCV, 2024 (LNCS), pp. 430–448. doi · arXiv
- F. Yu, J. Gu, Z. Li, J. Hu, X. Kong, X. Wang, J. He, Y. Qiao and C. Dong, “Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild,” in Proc. IEEE/CVF CVPR, 2024, pp. 25669–25680. doi · arXiv
- Y. Wang, W. Yang, X. Chen, Y. Wang, L. Guo, L.-P. Chau, Z. Liu, Y. Qiao, A. C. Kot and B. Wen, “SinSR: Diffusion-Based Image Super-Resolution in a Single Step,” in Proc. IEEE/CVF CVPR, 2024, pp. 25796–25805. doi · arXiv
- R. Wu, L. Sun, Z. Ma and L. Zhang, “One-Step Effective Diffusion Network for Real-World Image Super-Resolution,” in Proc. NeurIPS, vol. 37, 2024, pp. 92529–92553. doi · arXiv
- Z. Yue, K. Liao and C. C. Loy, “Arbitrary-steps Image Super-resolution via Diffusion Inversion,” in Proc. IEEE/CVF CVPR, 2025, pp. 23153–23163. doi · arXiv
- L. Dong, Q. Fan, Y. Guo, Z. Wang, Q. Zhang, J. Chen, Y. Luo and C. Zou, “TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution,” in Proc. IEEE/CVF CVPR, 2025, pp. 23174–23184. doi · arXiv
- Y. Lipman, R. T. Q. Chen, H. Ben-Hamu, M. Nickel and M. Le, “Flow Matching for Generative Modeling,” in Proc. ICLR, 2023. arXiv
- X. Liu, C. Gong and Q. Liu, “Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow,” in Proc. ICLR, 2023. arXiv
- G. Ohayon, T. Michaeli and M. Elad, “Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration,” in Proc. ICLR, 2025. arXiv
- S. Martin, A. Gagneux, P. Hagemann and G. Steidl, “PnP-Flow: Plug-and-Play Image Restoration with Flow Matching,” in Proc. ICLR, 2025. arXiv
- S. Bhadra, V. A. Kelkar, F. J. Brooks and M. A. Anastasio, “On Hallucinations in Tomographic Image Reconstruction,” IEEE Transactions on Medical Imaging, vol. 40, no. 11, pp. 3249–3260, 2021. doi · arXiv
- W. Ren, R. Goyal, Z. Hu, T. T. Aumentado-Armstrong, I. Mohomed and A. Levinshtein, “Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolution,” arXiv:2507.14367, 2025. arXiv
- A. N. Angelopoulos, A. P. Kohli, S. Bates, M. I. Jordan, J. Malik, T. Alshaabi, S. Upadhyayula and Y. Romano, “Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging,” in Proc. ICML, PMLR 162, 2022. proceedings · arXiv
- R. Zhang, P. Isola, A. A. Efros, E. Shechtman and O. Wang, “The Unreasonable Effectiveness of Deep Features as a Perceptual Metric,” in Proc. IEEE/CVF CVPR, 2018, pp. 586–595. doi · arXiv
- Z. Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli, “Image Quality Assessment: From Error Visibility to Structural Similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600–612, 2004. doi
- M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler and S. Hochreiter, “GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium,” in Proc. NeurIPS (NIPS), 2017. arXiv
- A. Mittal, R. Soundararajan and A. C. Bovik, “Making a ‘Completely Blind’ Image Quality Analyzer,” IEEE Signal Processing Letters, vol. 20, no. 3, pp. 209–212, 2013. doi
- J. Ke, Q. Wang, Y. Wang, P. Milanfar and F. Yang, “MUSIQ: Multi-scale Image Quality Transformer,” in Proc. IEEE/CVF ICCV, 2021, pp. 5128–5137. doi · arXiv
- J. Wang, K. C. K. Chan and C. C. Loy, “Exploring CLIP for Assessing the Look and Feel of Images,” in Proc. AAAI, vol. 37, no. 2, 2023, pp. 2555–2563. doi · arXiv
- X. Li, Y. Ren, X. Jin, C. Lan, X. Wang, W. Zeng, X. Wang and Z. Chen, “Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey,” International Journal of Computer Vision, vol. 133, no. 11, pp. 8078–8108, 2025. doi · arXiv
- G. Daras, H. Chung, C.-H. Lai, Y. Mitsufuji, J. C. Ye, P. Milanfar, A. G. Dimakis and M. Delbracio, “A Survey on Diffusion Models for Inverse Problems,” arXiv:2410.00083, 2024. arXiv
- B. B. Moser, A. S. Shanbhag, F. Raue, S. Frolov, S. Palacio and A. Dengel, “Diffusion Models, Image Super-Resolution, and Everything: A Survey,” IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 7, pp. 11793–11813, 2025. doi · arXiv
- W. Xia, Y. Zhang, Y. Yang, J.-H. Xue, B. Zhou and M.-H. Yang, “GAN Inversion: A Survey,” IEEE TPAMI, vol. 45, no. 3, pp. 3121–3138, 2023. doi · arXiv
- Y. Song and S. Ermon, “Generative Modeling by Estimating Gradients of the Data Distribution,” in Proc. NeurIPS, 2019. arXiv
- H. Chung, J. Kim, S. Kim and J. C. Ye, “Parallel Diffusion Models of Operator and Image for Blind Inverse Problems,” in Proc. IEEE/CVF CVPR, 2023, pp. 6059–6069. paper