UG${}^{2+}$ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments

Abstract

The UG${}^{2+}$ challenge in IEEE CVPR 2019 aims to evoke a comprehensive discussion and exploration about how low-level vision techniques can benefit the high-level automatic visual recognition in various scenarios. In its second track, we focus on object or face detection in poor visibility enhancements caused by bad weathers (haze, rain) and low light conditions. While existing enhancement methods are empirically expected to help the high-level end task, that is observed to not always be the case in practice. To provide a more thorough examination and fair comparison, we introduce three benchmark sets collected in real-world hazy, rainy, and low-light conditions, respectively, with annotate objects/faces annotated. To our best knowledge, this is the first and currently largest effort of its kind. Baseline results by cascading existing enhancement and detection models are reported, indicating the highly challenging nature of our new data as well as the large room for further technical innovations. We expect a large participation from the broad research community to address these challenges together.

A summary paper on datasets, fact sheets, baseline results, challenge results, and winning methods in UG${}^{2+}$ Challenge (Track 2). More materials are provided in http://www.ug2challenge.org/index.html

References in corpus (12)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• YOLOv3: An Incremental Improvement
• Two-Stream Convolutional Networks for Action Recognition in Videos
• DehazeNet: An End-to-End System for Single Image Haze Removal
• Clearing the Skies: A deep network architecture for single-image rain removal
• A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement
• Deep Retinex Decomposition for Low-Light Enhancement
• Real-world Noisy Image Denoising: A New Benchmark
• An All-in-One Network for Dehazing and Beyond
• Bridging the Gap Between Computational Photography and Visual Recognition
• Improved Techniques for Learning to Dehaze and Beyond: A Collective Study
• End-to-End United Video Dehazing and Detection

Cited by in corpus (8)

• EnlightenGAN: Deep Light Enhancement without Paired Supervision
• Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement
• Low-Light Image and Video Enhancement Using Deep Learning: A Survey
• Segmentation-Aware Image Denoising without Knowing True Segmentation
• Enhancement by Your Aesthetic: An Intelligible Unsupervised Personalized Enhancer for Low-Light Images
• Recurrent Exposure Generation for Low-Light Face Detection
• Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation
• DAVID: Dual-Attentional Video Deblurring