most citedDual-former: Hybrid Self-attention Transformer for Efficient Image Restoration

11 citations · 19 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2024

Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors

Yunlong Lin, Zhenqi Fu, Kairun Wen +7

Low-light image enhancement (LIE) aims at precisely and efficiently recovering an image degraded in poor illumination environments. Recent advanced LIE techniques are using deep ne…

cs.CV2024

Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint

Sixiang Chen, Tian Ye, Kai Zhang +3

Recent advancements in adverse weather restoration have shown potential, yet the unpredictable and varied combinations of weather degradations in the real world pose significant ch…

cs.CV202211 cited

Dual-former: Hybrid Self-attention Transformer for Efficient Image Restoration

Sixiang Chen, Tian Ye, Yun Liu +1

Recently, image restoration transformers have achieved comparable performance with previous state-of-the-art CNNs. However, how to efficiently leverage such architectures remains a…

cs.CV2022

Underwater Light Field Retention : Neural Rendering for Underwater Imaging

Tian Ye, Sixiang Chen, Yun Liu +3

Underwater Image Rendering aims to generate a true-tolife underwater image from a given clean one, which could be applied to various practical applications such as underwater image…

cs.CV20225 cited

Towards Efficient Single Image Dehazing and Desnowing

Tian Ye, Sixiang Chen, Yun Liu +2

Removing adverse weather conditions like rain, fog, and snow from images is a challenging problem. Although the current recovery algorithms targeting a specific condition have made…

cs.CV20223 cited

Mutual Learning for Domain Adaptation: Self-distillation Image Dehazing Network with Sample-cycle

Tian Ye, Yun Liu, Yunchen Zhang +2

Deep learning-based methods have made significant achievements for image dehazing. However, most of existing dehazing networks are concentrated on training models using simulated h…