paper-with-me

홈 › Papers

UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement

2024-04-22 · CVPR 2024 1 · Yaofeng Xie, Lingwei Kong, Kai Chen, Ziqiang Zheng, Xiao Yu, Zhibin Yu, Bing Zheng

Learning-based underwater image enhancement (UIE) methods have made great progress. However, the lack of large-scale and high-quality paired training samples has become the main bottleneck hindering the development of UIE. The inter-frame information in underwater videos can accelerate or optimize the UIE process. Thus, we constructed the first large-scale high-resolution underwater video enhancement benchmark (UVEB) to promote the development of underwater vision.It contains 1,308 pairs of video sequences and more than 453,000 high-resolution with 38\% Ultra-High-Definition (UHD) 4K frame pairs. UVEB comes from multiple countries, containing various scenes and video degradation types to adapt to diverse and complex underwater environments. We also propose the first supervised underwater video enhancement method, UVE-Net. UVE-Net converts the current frame information into convolutional kernels and passes them to adjacent frames for efficient inter-frame information exchange. By fully utilizing the redundant degraded information of underwater videos, UVE-Net completes video enhancement better. Experiments show the effective network design and good performance of UVE-Net.

📄 PDF Abstract BibTeX arXiv:2404.14542

Code (1)

yzbouc/uveb 공식 구현 pytorch

Tasks

4kImage EnhancementUIEVideo Enhancement

Similar Papers 제목 키워드 기반

From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal

2023-08-07 · ICCV 2023 1 · Yun Guo, Xueyao Xiao, Yi Chang, Shumin Deng 외

Learning-based image deraining methods have made great progress. However, the lack of large-scale high-quality paired training samples is the main bottleneck to hamper the real image deraining (RID). To address this dile…

DiversityRain RemovalSingle Image Deraining

Improving and Assessing Anomaly Detectors for Large-Scale Settings

2021-09-29 · Dan Hendrycks, Steven Basart, Mantas Mazeika, Andy Zou 외

Detecting out-of-distribution examples is important for safety-critical machine learning applications such as detecting novel biological phenomena and self-driving cars. However, existing research mainly focuses on simpl…

Anomaly SegmentationOut-of-Distribution DetectionSegmentationSelf-Driving Cars

DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection

2020-01-09 · CVPR 2020 6 · Liming Jiang, Ren Li, Wayne Wu, Chen Qian 외

We present our on-going effort of constructing a large-scale benchmark for face forgery detection. The first version of this benchmark, DeeperForensics-1.0, represents the largest face forgery detection dataset by far, w…

DiversityFace SwappingVideo Forensics

When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmark

2024-07-15 · Junhong Lin, Xiaojie Guo, Shuaicheng Zhang, Yada Zhu 외

Graph mining has become crucial in fields such as social science, finance, and cybersecurity. Many large-scale real-world networks exhibit both heterogeneity, where multiple node and edge types exist in the graph, and he…

BenchmarkingGraph LearningGraph MiningModel Selection+1

Scaling Out-of-Distribution Detection for Real-World Settings

2019-11-25 · Dan Hendrycks, Steven Basart, Mantas Mazeika, Andy Zou 외

Detecting out-of-distribution examples is important for safety-critical machine learning applications such as detecting novel biological phenomena and self-driving cars. However, existing research mainly focuses on simpl…

Anomaly SegmentationOut-of-Distribution DetectionSegmentationSelf-Driving Cars+1