activity
20212025
most citedDemystifying Oversmoothing in Attention-Based Graph Neural Networks

10 citations · 40 across the 8 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2025

Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration

Junyuan Deng, Xinyi Wu, Yongxing Yang +3

Recently, pre-trained text-to-image (T2I) models have been extensively adopted for real-world image restoration because of their powerful generative prior. However, controlling the…

cs.CV2023★ 1 cited

Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network

Canyu Zhang, Zhenyao Wu, Xinyi Wu +2

3D point cloud semantic segmentation aims to group all points into different semantic categories, which benefits important applications such as point cloud scene reconstruction and…

cs.CV2023★ 10 cited

Parametric Surface Constrained Upsampler Network for Point Cloud

Pingping Cai, Zhenyao Wu, Xinyi Wu +1

Designing a point cloud upsampler, which aims to generate a clean and dense point cloud given a sparse point representation, is a fundamental and challenging problem in computer vi…

cs.CV2022★ 4 cited

Cross-domain Few-shot Segmentation with Transductive Fine-tuning

Yuhang Lu, Xinyi Wu, Zhenyao Wu +1

Few-shot segmentation (FSS) expects models trained on base classes to work on novel classes with the help of a few support images. However, when there exists a domain gap between t…

cs.CV2021★ 7 cited

DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation

Xinyi Wu, Zhenyao Wu, Hao Guo +2

Semantic segmentation of nighttime images plays an equally important role as that of daytime images in autonomous driving, but the former is much more challenging due to poor illum…

cs.CV2021★ 3 cited

From Shadow Generation to Shadow Removal

Zhihao Liu, Hui Yin, Xinyi Wu +3

Shadow removal is a computer-vision task that aims to restore the image content in shadow regions. While almost all recent shadow-removal methods require shadow-free images for tra…