Improved Techniques for Learning to Dehaze and Beyond: A Collective Study

Abstract

Here we explore two related but important tasks based on the recently released REalistic Single Image DEhazing (RESIDE) benchmark dataset: (i) single image dehazing as a low-level image restoration problem; and (ii) high-level visual understanding (e.g., object detection) of hazy images. For the first task, we investigated a variety of loss functions and show that perception-driven loss significantly improves dehazing performance. In the second task, we provide multiple solutions including using advanced modules in the dehazing-detection cascade and domain-adaptive object detectors. In both tasks, our proposed solutions significantly improve performance. GitHub repository URL is: https://github.com/guanlongzhao/dehaze

arXiv commentupdated: typo fixed and some other improvements on writing

References in corpus (8)

• DehazeNet: An End-to-End System for Single Image Haze Removal
• Focal Loss for Dense Object Detection
• An All-in-One Network for Dehazing and Beyond
• Densely Connected Pyramid Dehazing Network
• Studying Very Low Resolution Recognition Using Deep Networks
• Benchmarking Single Image Dehazing and Beyond
• When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach
• Robust Emotion Recognition from Low Quality and Low Bit Rate Video: A Deep Learning Approach

Cited by in corpus (8)

• R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network
• EnlightenGAN: Deep Light Enhancement without Paired Supervision
• FAMED-Net: A Fast and Accurate Multi-scale End-to-end Dehazing Network
• All-In-One Underwater Image Enhancement using Domain-Adversarial Learning
• UG${}^{2+}$ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments
• Benchmarking Single Image Dehazing and Beyond
• Advanced Multiple Linear Regression Based Dark Channel Prior Applied on Dehazing Image and Generating Synthetic Haze
• Debiased Subjective Assessment of Real-World Image Enhancement