57 citations · 95 across the 12 of their papers we have counts for
13 papers · 1 filter
PointSFDA: Source-free Domain Adaptation for Point Cloud Completion
Xing He, Zhe Zhu, Liangliang Nan +3
Conventional methods for point cloud completion, typically trained on synthetic datasets, face significant challenges when applied to out-of-distribution real-world scans. In this…
Cross-BERT for Point Cloud Pretraining
Xin Li, Peng Li, Zeyong Wei +7
Introducing BERT into cross-modal settings raises difficulties in its optimization for handling multiple modalities. Both the BERT architecture and training objective need to be ad…
SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generator
Zhe Zhu, Honghua Chen, Xing He +3
In this paper, we propose a novel network, SVDFormer, to tackle two specific challenges in point cloud completion: understanding faithful global shapes from incomplete point clouds…
Rethinking Generative Methods for Image Restoration in Physics-based Vision: A Theoretical Analysis from the Perspective of Information
Xudong Kang, Haoran Xie, Man-Leung Wong +1
End-to-end generative methods are considered a more promising solution for image restoration in physics-based vision compared with the traditional deconstructive methods based on h…
ImLiDAR: Cross-Sensor Dynamic Message Propagation Network for 3D Object Detection
Yiyang Shen, Rongwei Yu, Peng Wu +4
LiDAR and camera, as two different sensors, supply geometric (point clouds) and semantic (RGB images) information of 3D scenes. However, it is still challenging for existing method…
UTOPIC: Uncertainty-aware Overlap Prediction Network for Partial Point Cloud Registration
Zhilei Chen, Honghua Chen, Lina Gong +5
High-confidence overlap prediction and accurate correspondences are critical for cutting-edge models to align paired point clouds in a partial-to-partial manner. However, there inh…
CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completion
Zhe Zhu, Liangliang Nan, Haoran Xie +4
How will you repair a physical object with some missings? You may imagine its original shape from previously captured images, recover its overall (global) but coarse shape first, a…
Dynamic Message Propagation Network for RGB-D Salient Object Detection
Baian Chen, Zhilei Chen, Xiaowei Hu +4
This paper presents a novel deep neural network framework for RGB-D salient object detection by controlling the message passing between the RGB images and depth maps on the feature…
AGConv: Adaptive Graph Convolution on 3D Point Clouds
Mingqiang Wei, Zeyong Wei, Haoran Zhou +9
Convolution on 3D point clouds is widely researched yet far from perfect in geometric deep learning. The traditional wisdom of convolution characterises feature correspondences ind…
UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning
Yongzhen Wang, Xuefeng Yan, Fu Lee Wang +4
While the wisdom of training an image dehazing model on synthetic hazy data can alleviate the difficulty of collecting real-world hazy/clean image pairs, it brings the well-known d…
Detail-recovery Image Deraining via Dual Sample-augmented Contrastive Learning
Yiyang Shen, Mingqiang Wei, Sen Deng +5
The intricacy of rainy image contents often leads cutting-edge deraining models to image degradation including remnant rain, wrongly-removed details, and distorted appearance. Such…
Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds
Haoran Zhou, Honghua Chen, Yingkui Zhang +6
Point normal, as an intrinsic geometric property of 3D objects, not only serves conventional geometric tasks such as surface consolidation and reconstruction, but also facilitates…
Adaptive Graph Convolution for Point Cloud Analysis
Haoran Zhou, Yidan Feng, Mingsheng Fang +3
Convolution on 3D point clouds that generalized from 2D grid-like domains is widely researched yet far from perfect. The standard convolution characterises feature correspondences…