UGPNet: Universal Generative Prior for Image Restoration
원문 초록
Recent image restoration methods can be broadly categorized into two classes: (1) regression methods that recover the rough structure of the original image without synthesizing high-frequency details and (2) generative methods that synthesize perceptually-realistic high-frequency details even though the resulting image deviates from the original structure of the input. While both directions have been extensively studied in isolation, merging their benefits with a single framework has been rarely studied. In this paper, we propose UGPNet, a universal image restoration framework that can effectively achieve the benefits of both approaches by simply adopting a pair of an existing regression model and a generative model. UGPNet first restores the image structure of a degraded input using a regression model and synthesizes a perceptually-realistic image with a generative model on top of the regressed output. UGPNet then combines the regressed output and the synthesized output, resulting in a final result that faithfully reconstructs the structure of the original image in addition to perceptually-realistic textures. Our extensive experiments on deblurring, denoising, and super-resolution demonstrate that UGPNet can successfully exploit both regression and generative methods for high-fidelity image restoration.
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
Multi-Step Guided Diffusion for Image Restoration on Edge Devices: Toward Lightweight Perception in Embodied AI
Visual-Instructed Degradation Diffusion for All-in-One Image Restoration
Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching
Plug-and-Play Linear Attention for Pre-trained Image and Video Restoration Models
Exploring Diffusion with Test-Time Training on Efficient Image Restoration
토론
이 논문과 연결된 포럼 글이 아직 없습니다.