Image Dehazing Transformer with Transmission-Aware 3D Position Embedding
Authors:
Top Cited Papers
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5802-5810
Abstract
Despite single image dehazing has been made promising progress with Convolutional Neural Networks (CNNs), the inherent equivariance and locality of convolution still bottleneck deharing performance. Though Transformer has occupied various computer vision tasks, directly leveraging Transformer for image dehazing is challenging: 1) it tends to result in ambiguous and coarse details that are undesired for image reconstruction; 2) previous position embedding of Transformer is provided in logic or spatial position order that neglects the variational haze densities, which results in the sub-optimal dehazlng performance. The key insight of this study is to investigate how to combine CNN and Transformer for image dehazing. To solve the feature inconsistency issue between Transformer and CNN, we propose to modulate CNN features via learning modulation matrices (i.e., coefficient matrix and bias matrix) conditioned on Transformer features instead of simple feature addition or concatenation. The feature modulation naturally inherits the global context modeling capability of Transformer and the local representation capability of CNN. We bring a haze density-related prior into Trans-former via a novel transmission-aware 3D position embedding module, which not only provides the relative position but also suggests the haze density of different spatial regions. Extensive experiments demonstrate that our method, DeHamer, attains state-of-the-art performance on several image dehazing benchmarks.Keywords
Funding Information
- National Natural Science Foundation of China (61922046)
This publication has 19 references indexed in Scilit:
- Dense-Haze: A Benchmark for Image Dehazing with Dense-Haze and Haze-Free Images2019
- Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform2018
- Densely Connected Pyramid Dehazing Network2018
- Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization2017
- AOD-Net: All-in-One Dehazing Network2017
- Pyramid Scene Parsing Network2017
- DehazeNet: An End-to-End System for Single Image Haze RemovalIEEE Transactions on Image Processing, 2016
- Dehazing Using Color-LinesACM Transactions on Graphics, 2014
- Single Image Haze Removal Using Dark Channel PriorIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Vision Through the Atmosphere1952