paper-with-me

Papers

Diffusion Posterior Proximal Sampling for Image Restoration

2024-02-25 · Hongjie Wu, Linchao He, Mingqin Zhang, Dongdong Chen, Kunming Luo, Mengting Luo, Ji-Zhe Zhou, Hu Chen, Jiancheng Lv

Diffusion models have demonstrated remarkable efficacy in generating high-quality samples. Existing diffusion-based image restoration algorithms exploit pre-trained diffusion models to leverage data priors, yet they still preserve elements inherited from the unconditional generation paradigm. These strategies initiate the denoising process with pure white noise and incorporate random noise at each generative step, leading to over-smoothed results. In this paper, we present a refined paradigm for diffusion-based image restoration. Specifically, we opt for a sample consistent with the measurement identity at each generative step, exploiting the sampling selection as an avenue for output stability and enhancement. The number of candidate samples used for selection is adaptively determined based on the signal-to-noise ratio of the timestep. Additionally, we start the restoration process with an initialization combined with the measurement signal, providing supplementary information to better align the generative process. Extensive experimental results and analyses validate that our proposed method significantly enhances image restoration performance while consuming negligible additional computational resources.

📄 PDF Abstract BibTeX arXiv:2402.16907

Code (1)

74587887/dpps_code 공식 구현 pytorch

Tasks

DenoisingImage Restoration

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
OPT OPT is a suite of decoder-only pre-trained transformers ranging from 125M to 175B parameters. The model uses an AdamW optimizer and weight decay of 0.1. It follows a linear…

Similar Papers 제목 키워드 기반

DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration

2025-04-30 · Hebaixu Wang, Jing Zhang, HaoNan Guo, Di Wang 외

Diffusion models have achieved remarkable progress in universal image restoration. While existing methods speed up inference by reducing sampling steps, substantial step intervals often introduce cumulative errors. Moreo…

Image RestorationNoise Estimation

Photo-Realistic Image Restoration in the Wild with Controlled Vision-Language Models

2024-04-15 · Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund 외

Though diffusion models have been successfully applied to various image restoration (IR) tasks, their performance is sensitive to the choice of training datasets. Typically, diffusion models trained in specific datasets …

Image GenerationImage RestorationLanguage ModelingLanguage Modelling+1

Integrating Reweighted Least Squares with Plug-and-Play Diffusion Priors for Noisy Image Restoration

2025-11-10 · Ji Li, Chao Wang arxiv

Existing plug-and-play image restoration methods typically employ off-the-shelf Gaussian denoisers as proximal operators within classical optimization frameworks based on variable splitting. Recently, denoisers induced b…

Image Restoration

LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling

2025-07-01 · Huaqiu Li, Yong Wang, Tongwen Huang, Hailang Huang 외

Unified image restoration is a significantly challenging task in low-level vision. Existing methods either make tailored designs for specific tasks, limiting their generalizability across various types of degradation, or…

Image RestorationUnified Image Restoration

From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling

2025-05-20 · Marien Renaud, Valentin De Bortoli, Arthur Leclaire, Nicolas Papadakis

We consider the problem of sampling distributions stemming from non-convex potentials with Unadjusted Langevin Algorithm (ULA). We prove the stability of the discrete-time ULA to drift approximations under the assumption…