paper-with-me

Papers

ForkGAN: Seeing into the Rainy Night

2020-08-01 · ECCV 2020 8 · Ziqiang Zheng, Yang Wu, Xinran Han, Jianbo Shi

We present a ForkGAN for task-agnostic image translation that can boost multiple vision tasks in adverse weather conditions. Three tasks of image localization/retrieval, semantic image segmentation, and object detection are evaluated. The key challenge is achieving high-quality image translation without any explicit supervision, or task awareness. Our innovation is a fork-shape generator with one encoder and two decoders that disentangles the domain-specific and domain-invariant information. We force the cyclic translation between the weather conditions to go through a common encoding space, and make sure the encoding features reveal no information about the domains. Experimental results show our algorithm produces state-of-the-art image synthesis results and boost three vision tasks' performances in adverse weathers.

📄 PDF Abstract BibTeX

Code (1)

zhengziqiang/forkgan 공식 구현 tf

Tasks

Image GenerationImage Segmentationobject-detectionObject DetectionRetrievalSemantic SegmentationTranslation

Similar Papers 제목 키워드 기반

Long Nights, Rainy Days, and Misspent Youth: Automatically Extracting and Categorizing Occasions Associated with Consumer Products.

2015-06-01 · WS 2015 6 · David Bracewell

Learning Rain Location Prior for Nighttime Deraining

2023-01-01 · ICCV 2023 1 · Fan Zhang, ShaoDi You, Yu Li, Ying Fu

Rain can significantly degrade image quality and visibility, making deraining a critical area of research in computer vision. Despite recent progress in learning-based deraining methods, there is a lack of focus on n…

Rain Removal

GTAV-NightRain: Photometric Realistic Large-scale Dataset for Night-time Rain Streak Removal

2022-10-10 · Fan Zhang, ShaoDi You, Yu Li, Ying Fu

Rain is transparent, which reflects and refracts light in the scene to the camera. In outdoor vision, rain, especially rain streaks degrade visibility and therefore need to be removed. In existing rain streak removal dat…

ProvRain: Rain-Adaptive Denoising and Vehicle Detection via MobileNet-UNet and Faster R-CNN

2025-11-24 · Aswinkumar Varathakumaran, Nirmala Paramanandham arxiv

Provident vehicle detection has a lot of scope in the detection of vehicle during night time. The extraction of features other than the headlamps of vehicles allows us to detect oncoming vehicles before they appear direc…

UniDA3D: A Unified Domain-Adaptive Framework for Multi-View 3D Object Detection

2026-03-30 · Hongjing Wu, Cheng Chi, Jinlin Wu, Yanzhao Su 외 arxiv

Camera-only 3D object detection is critical for autonomous driving, offering a cost-effective alternative to LiDAR based methods. In particular, multi-view 3D object detection has emerged as a promising direction due to …

Contrastive Learning3D Object DetectionAutonomous DrivingDomain Adaptation