Explorable Super Resolution
Yuval Bahat, Tomer Michaeli
2020Year
15Top-tier citations
Abstract
Low-res input Other perfectly consistent reconstructions produced with our approach Figure 1: Exploring HR explanations to an LR image. Existing SR methods (e.g. ESRGAN [26] ) output only one explanation to the input image. In contrast, our explorable SR framework allows producing infinite different perceptually satisfying HR images, that all identically match a given LR input, when down-sampled. Please zoom-in to view subtle details.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext ba473901-1d4f-49b5-87a8-fabbe9bbd95aCited by top-tier papers15
- SNIPS: Solving Noisy Inverse Problems StochasticallyBahjat Kawar, Gregory Vaksman, Michael EladNeurIPS 2021 · 263 citations
- Zero-Shot Image Restoration Using Denoising Diffusion Null-Space ModelYinhuai Wang, Jiwen Yu, Jian ZhangICLR 2023 · 94 citations
- A Theory of the Distortion-Perception Tradeoff in Wasserstein SpaceDror Freirich, Tomer Michaeli, Ron MeirNeurIPS 2021 · 77 citations
- GAN Prior Based Null-Space Learning for Consistent Super-resolutionYinhuai Wang, Yujie Hu, Jiwen Yu, Jian ZhangAAAI 2023 · 52 citations
- Reasons for the Superiority of Stochastic Estimators over Deterministic Ones: Robustness, Consistency and Perceptual QualityGuy Ohayon, Theo Joseph Adrai, Michael Elad, Tomer MichaeliICML 2023 · 18 citations
Builds on1
Related papers
- GLEAN: Generative Latent Bank for Large-Factor Image Super-ResolutionKelvin C. K. Chan, Xintao Wang, Xiangyu Xu, Jinwei Gu et al.CVPR 2021
- Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-ResolutionHyeonjae Kim, Dongjin Kim, Eugene Jin, Tae Hyun KimAAAI 2026 · 1 citation
- Deep Burst Super-ResolutionGoutam Bhat, Martin Danelljan, Luc Van Gool, Radu TimofteCVPR 2021
- NeRF-SR: High Quality Neural Radiance Fields using SupersamplingChen Wang, Xian Wu, Yuan-Chen Guo, Song-Hai Zhang et al.ACM MM 2022 · 115 citations
- Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image RescalingJingyun Liang, Andreas Lugmayr, Kai Zhang, Martin Danelljan et al.ICCV 2021 · 124 citations
