High-dimensional Assisted Generative Model for Color Image Restoration
On the map: Diffusion models → Inverse problems and image restoration
Abstract (arXiv)
This work presents an unsupervised deep learning scheme that exploiting high-dimensional assisted score-based generative model for color image restoration tasks. Considering that the sample number and internal dimension in score-based generative model have key influence on estimating the gradients of data distribution, two different high-dimensional ways are proposed: The channel-copy transformation increases the sample number and the pixel-scale transformation decreases feasible space dimension. Subsequently, a set of high-dimensional tensors represented by these transformations are used to train the network through denoising score matching. Then, sampling is performed by annealing Langevin dynamics and alternative data-consistency update. Furthermore, to alleviate the difficulty of learning high-dimensional representation, a progressive strategy is proposed to leverage the performance. The proposed unsupervised learning and iterative restoration algo-rithm, which involves a pre-trained generative network to obtain prior, has transparent and clear interpretation compared to other data-driven approaches. Experimental results on demosaicking and inpainting conveyed the remarkable performance and diversity of our proposed method.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 20 of its 56 references that are in the map. First posted on arXiv 14 Aug 2021.
Builds on
20 of 56 references.
References · 20
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
- 2013Auto-Encoding Variational Bayescited by 4,053
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
- 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
- 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
- 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
- 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
- 2014Semi-Supervised Learning with Deep Generative Modelscited by 496
- 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 408
- 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 307
- 2015DRAW: A Recurrent Neural Network For Image Generationcited by 191
- 2015Deep Convolutional Inverse Graphics Networkcited by 121
8 more
- 2020Generative Modeling with Denoising Auto-Encoders and Langevin Samplingcited by 119
- 2017Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problemscited by 107
- 2020Recurrent Feature Reasoning for Image Inpaintingcited by 107
- 2020Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizationscited by 102
- 2017Generative Face Completioncited by 79
- 2017Perceptual Adversarial Networks for Image-to-Image Transformationcited by 42
- 2019PEPSI++: Fast and Lightweight Network for Image Inpaintingcited by 24
- 2020Homotopic Gradients of Generative Density Priors for MR Image Reconstructioncited by 14
Built on by
Citing papers per year: 2022: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2021Wavelet Transform-assisted Adaptive Generative Modeling for Colorization
- 2023Generative Diffusion Prior for Unified Image Restoration and Enhancement
- 2024Multi-scale Conditional Generative Modeling for Microscopic Image Restoration
- 2022Megapixel Image Generation with Step-Unrolled Denoising Autoencoders
- 2021Generative Probabilistic Image Colorization
- 2023Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data
- 2024Posterior sampling via Langevin dynamics based on generative priors
- 2022Denoising Diffusion Restoration Models