Visual-in-Visual: A Unified and Efficient Baseline for Image Restoration

Recent years have witnessed remarkable progress in image restoration, yet achieving both high performance and efficiency remains a persistent challenge. To address this issue, we present VIVNet, a strong and efficient unified baseline designed to balance accuracy and practicality. Drawing inspiratio...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2026-03, Vol.PP, p.1-18
Main Authors: Cui, Yuning, Ren, Wenqi, Shi, Boxin, Knoll, Alois
Format: Article
Language:English
Subjects:
All-in-one image restoration
composite degradation
Computational modeling
Computer architecture
Degradation
efficient baseline
Encoding
Feature extraction
human vision
Image restoration
medical image processing
Multitasking
remote sensing
Retina
Transformers
ultra-high-definition image restoration
underwater image enhancement
unified network
Visualization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!