arXiv:2206.14373
Theoretical Perspectives on Deep Learning Methods in Inverse Problems
원문 초록
In recent years, there have been significant advances in the use of deep learning methods in inverse problems such as denoising, compressive sensing, inpainting, and super-resolution. While this line of works has predominantly been driven by practical algorithms and experiments, it has also given rise to a variety of intriguing theoretical problems. In this paper, we survey some of the prominent theoretical developments in this line of works, focusing in particular on generative priors, untrained neural network priors, and unfolding algorithms. In addition to summarizing existing results in these topics, we highlight several ongoing challenges and open problems.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
Plug-and-Play Linear Attention for Pre-trained Image and Video Restoration Models
Grids Often Outperform Implicit Neural Representations
Exploring Diffusion with Test-Time Training on Efficient Image Restoration
Zero-Shot Solving of Imaging Inverse Problems via Noise-Refined Likelihood Guided Diffusion Models
Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.