U-shaped Vision Mamba for Single Image Dehazing

Code

• github.com/zzr-idam/uvm-net
  OfficialIn paperpytorch★ 163

Abstract

Currently, Transformer is the most popular architecture for image dehazing, but due to its large computational complexity, its ability to handle long-range dependency is limited on resource-constrained devices. To tackle this challenge, we introduce the U-shaped Vision Mamba (UVM-Net), an efficient single-image dehazing network. Inspired by the State Space Sequence Models (SSMs), a new deep sequence model known for its power to handle long sequences, we design a Bi-SSM block that integrates the local feature extraction ability of the convolutional layer with the ability of the SSM to capture long-range dependencies. Extensive experimental results demonstrate the effectiveness of our method. Our method provides a more highly efficient idea of long-range dependency modeling for image dehazing as well as other image restoration tasks. The URL of the code is https://github.com/zzr-idam/UVM-Net. Our method takes only 0.009 seconds to infer a 325 325 resolution image (100FPS) without I/O handling time.

Tasks

Reproductions