paper-with-me

Papers

Improving Diffusion Models for Inverse Problems using Manifold Constraints

2022-06-02 · Hyungjin Chung, Byeongsu Sim, Dohoon Ryu, Jong Chul Ye

Recently, diffusion models have been used to solve various inverse problems in an unsupervised manner with appropriate modifications to the sampling process. However, the current solvers, which recursively apply a reverse diffusion step followed by a projection-based measurement consistency step, often produce suboptimal results. By studying the generative sampling path, here we show that current solvers throw the sample path off the data manifold, and hence the error accumulates. To address this, we propose an additional correction term inspired by the manifold constraint, which can be used synergistically with the previous solvers to make the iterations close to the manifold. The proposed manifold constraint is straightforward to implement within a few lines of code, yet boosts the performance by a surprisingly large margin. With extensive experiments, we show that our method is superior to the previous methods both theoretically and empirically, producing promising results in many applications such as image inpainting, colorization, and sparse-view computed tomography. Code available https://github.com/HJ-harry/MCG_diffusion

📄 PDF Abstract BibTeX arXiv:2206.00941

Code (2)

hj-harry/mcg_diffusion 공식 구현 jax
gzhu06/MCG-ipynb

Tasks

ColorizationImage Inpainting

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…

Similar Papers 제목 키워드 기반

EquiReg: Equivariance Regularized Diffusion for Inverse Problems

2025-05-29 · Bahareh Tolooshams, Aditi Chandrashekar, Rayhan Zirvi, Abbas Mammadov 외

Diffusion models represent the state-of-the-art for solving inverse problems such as image restoration tasks. In the Bayesian framework, diffusion-based inverse solvers incorporate a likelihood term to guide the prior sa…

Image Restoration

Diffusion State-Guided Projected Gradient for Inverse Problems

2024-10-04 · Rayhan Zirvi, Bahareh Tolooshams, Anima Anandkumar

Recent advancements in diffusion models have been effective in learning data priors for solving inverse problems. They leverage diffusion sampling steps for inducing a data prior while using a measurement guidance gradie…

Image Restoration

Diffusion Posterior Sampling for General Noisy Inverse Problems

2022-09-29 · Hyungjin Chung, Jeongsol Kim, Michael T. McCann, Marc L. Klasky 외

Diffusion models have been recently studied as powerful generative inverse problem solvers, owing to their high quality reconstructions and the ease of combining existing iterative solvers. However, most works focus on s…

DeblurringRetrieval

Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency

2023-07-16 · Bowen Song, Soo Min Kwon, Zecheng Zhang, Xinyu Hu 외

Diffusion models have recently emerged as powerful generative priors for solving inverse problems. However, training diffusion models in the pixel space are both data-intensive and computationally demanding, which restri…

Decoder

CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models

2024-06-12 · Hyungjin Chung, Jeongsol Kim, Geon Yeong Park, Hyelin Nam 외

Classifier-free guidance (CFG) is a fundamental tool in modern diffusion models for text-guided generation. Although effective, CFG has notable drawbacks. For instance, DDIM with CFG lacks invertibility, complicating ima…

Image Generationtext-guided-generationText to Image GenerationText-to-Image Generation