10 citations · 49 across the 12 of their papers we have counts for
13 papers
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…
Demystifying Oversmoothing in Attention-Based Graph Neural Networks
Xinyi Wu, Amir Ajorlou, Zihui Wu +1
Oversmoothing in Graph Neural Networks (GNNs) refers to the phenomenon where increasing network depth leads to homogeneous node representations. While previous work has established…
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…
Automatic Camera Trajectory Control with Enhanced Immersion for Virtual Cinematography
Xinyi Wu, Haohong Wang, Aggelos K. Katsaggelos
User-generated cinematic creations are gaining popularity as our daily entertainment, yet it is a challenge to master cinematography for producing immersive contents. Many existing…
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…
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…
PLMCL: Partial-Label Momentum Curriculum Learning for Multi-Label Image Classification
Rabab Abdelfattah, Xin Zhang, Zhenyao Wu +3
Multi-label image classification aims to predict all possible labels in an image. It is usually formulated as a partial-label learning problem, given the fact that it could be expe…
Multi-scale Feature Aggregation for Crowd Counting
Xiaoheng Jiang, Xinyi Wu, Hisham Cholakkal +5
Convolutional Neural Network (CNN) based crowd counting methods have achieved promising results in the past few years. However, the scale variation problem is still a huge challeng…
CRFormer: A Cross-Region Transformer for Shadow Removal
Jin Wan, Hui Yin, Zhenyao Wu +3
Aiming to restore the original intensity of shadow regions in an image and make them compatible with the remaining non-shadow regions without a trace, shadow removal is a very chal…
Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation
Xinyi Wu, Zhenyao Wu, Yuhang Lu +2
In this paper, we tackle the problem of one-shot unsupervised domain adaptation (OSUDA) for semantic segmentation where the segmentors only see one unlabeled target image during tr…
ATLANTIS: A Benchmark for Semantic Segmentation of Waterbody Images
Seyed Mohammad Hassan Erfani, Zhenyao Wu, Xinyi Wu +2
Vision-based semantic segmentation of waterbodies and nearby related objects provides important information for managing water resources and handling flooding emergency. However, t…
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…
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…