168 citations · 628 across the 31 of their papers we have counts for
7 papers · 1 filter
Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method
Tao Wang, Kaihao Zhang, Tianrun Shen +3
As the quality of optical sensors improves, there is a need for processing large-scale images. In particular, the ability of devices to capture ultra-high definition (UHD) images a…
Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning
Tao Wang, Guangpin Tao, Wanglong Lu +4
Image restoration under hazy weather condition, which is called single image dehazing, has been of significant interest for various computer vision applications. In recent years, d…
SJ-HD^2R: Selective Joint High Dynamic Range and Denoising Imaging for Dynamic Scenes
Wei Li, Shuai Xiao, Tianhong Dai +4
Ghosting artifacts, motion blur, and low fidelity in highlight are the main challenges in High Dynamic Range (HDR) imaging from multiple Low Dynamic Range (LDR) images. These issue…
Geometric Synthesis: A Free lunch for Large-scale Palmprint Recognition Model Pretraining
Kai Zhao, Lei Shen, Yingyi Zhang +6
Palmprints are private and stable information for biometric recognition. In the deep learning era, the development of palmprint recognition is limited by the lack of sufficient tra…
Single UHD Image Dehazing via Interpretable Pyramid Network
Boxue Xiao, Zhuoran Zheng, Xiang Chen +3
Currently, most single image dehazing models cannot run an ultra-high-resolution (UHD) image with a single GPU shader in real-time. To address the problem, we introduce the princip…
LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling
Xu Wang, Yi Jin, Yigang Cen +3
Compared with traditional task-irrelevant downsampling methods, task-oriented neural networks have shown improved performance in point cloud downsampling range. Recently, Transform…
SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations
Tao Wang, Jun Hao Liew, Yu Li +2
Recent state-of-the-art one-stage instance segmentation model SOLO divides the input image into a grid and directly predicts per grid cell object masks with fully-convolutional net…