Multi-Scale Boosted Dehazing Network with Dense Feature Fusion

Abstract

In this paper, we propose a Multi-Scale Boosted Dehazing Network with Dense Feature Fusion based on the U-Net architecture. The proposed method is designed based on two principles, boosting and error feedback, and we show that they are suitable for the dehazing problem. By incorporating the Strengthen-Operate-Subtract boosting strategy in the decoder of the proposed model, we develop a simple yet effective boosted decoder to progressively restore the haze-free image. To address the issue of preserving spatial information in the U-Net architecture, we design a dense feature fusion module using the back-projection feedback scheme. We show that the dense feature fusion module can simultaneously remedy the missing spatial information from high-resolution features and exploit the non-adjacent features. Extensive evaluations demonstrate that the proposed model performs favorably against the state-of-the-art approaches on the benchmark datasets as well as real-world hazy images.

Accepted by CVPR 2020. The code are available at https://github.com/BookerDeWitt/MSBDN-DFF

References in corpus (6)

• YOLOv3: An Incremental Improvement
• DehazeNet: An End-to-End System for Single Image Haze Removal
• Semantic Foggy Scene Understanding with Synthetic Data
• Multi-Scale Dense Networks for Resource Efficient Image Classification
• Gated Fusion Network for Joint Image Deblurring and Super-Resolution
• End-to-End United Video Dehazing and Detection

Cited by in corpus (3)

• Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning
• Contrastive Learning for Compact Single Image Dehazing
• From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data