98 citations · 168 across the 31 of their papers we have counts for
29 papers · 1 filter
Levy-Driven Correspondence Estimation for Registration
Qianliang Wu, Jiaqi Yang, Wankou Yang +4
Finding reliable point correspondences is difficult when point clouds have low overlap or undergo non-rigid deformation. Iterative refinement can correct uncertain matches, but cos…
BridgeMatch: Conditional Transport Bridges in Matching Matrix Space for 3D Deformable Registration
Qianliang Wu, Haobo Jiang, Guangwei Gao +5
Reliable matching between partially observed, deforming point clouds requires global context and fine geometric detail. Coarse candidate selection can exclude correct fine-level co…
Diff-Reg v2: Diffusion-Based Matching Matrix Estimation for Image Matching and 3D Registration
Qianliang Wu, Haobo Jiang, Yaqing Ding +5
Establishing reliable correspondences is crucial for all registration tasks, including 2D image registration, 3D point cloud registration, and 2D-3D image-to-point cloud registrati…
FastPCI: Motion-Structure Guided Fast Point Cloud Frame Interpolation
Tianyu Zhang, Guocheng Qian, Jin Xie +1
Point cloud frame interpolation is a challenging task that involves accurate scene flow estimation across frames and maintaining the geometry structure. Prevailing techniques often…
Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splatting
Jiawei Xu, Zexin Fan, Jian Yang +1
Recently, Gaussian splatting has received more and more attention in the field of static scene rendering. Due to the low computational overhead and inherent flexibility of explicit…
Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformer
Yang Wu, Kaihua Zhang, Jianjun Qian +2
The complex traffic environment and various weather conditions make the collection of LiDAR data expensive and challenging. Achieving high-quality and controllable LiDAR data gener…
Diff-Reg v1: Diffusion Matching Model for Registration Problem
Qianliang Wu, Haobo Jiang, Lei Luo +4
Establishing reliable correspondences is essential for registration tasks such as 3D and 2D3D registration. Existing methods commonly leverage geometric or semantic point features…
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation
Haobo Jiang, Mathieu Salzmann, Zheng Dang +2
In this paper, we introduce an SE(3) diffusion model-based point cloud registration framework for 6D object pose estimation in real-world scenarios. Our approach formulates the 3D…
SGNet: Salient Geometric Network for Point Cloud Registration
Qianliang Wu, Yaqing Ding, Lei Luo +5
Point Cloud Registration (PCR) is a critical and challenging task in computer vision. One of the primary difficulties in PCR is identifying salient and meaningful points that exhib…
Self-Supervised 3D Scene Flow Estimation Guided by Superpoints
Yaqi Shen, Le Hui, Jin Xie +1
3D scene flow estimation aims to estimate point-wise motions between two consecutive frames of point clouds. Superpoints, i.e., points with similar geometric features, are usually…
Robust Outlier Rejection for 3D Registration with Variational Bayes
Haobo Jiang, Zheng Dang, Zhen Wei +3
Learning-based outlier (mismatched correspondence) rejection for robust 3D registration generally formulates the outlier removal as an inlier/outlier classification problem. The co…
Graph Matching Optimization Network for Point Cloud Registration
Qianliang Wu, Yaqi Shen, Haobo Jiang +5
Point Cloud Registration is a fundamental and challenging problem in 3D computer vision. Recent works often utilize the geometric structure information in point feature embedding o…
Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentation
Linghua Tang, Le Hui, Jin Xie
Due to the few annotated labels of 3D point clouds, how to learn discriminative features of point clouds to segment object instances is a challenging problem. In this paper, we pro…
Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking
Haobo Jiang, Kaihao Lan, Le Hui +3
Learning robust feature matching between the template and search area is crucial for 3D Siamese tracking. The core of Siamese feature matching is how to assign high feature similar…
Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching
Yikai Bian, Le Hui, Jianjun Qian +1
Unsupervised domain adaptation for point cloud semantic segmentation has attracted great attention due to its effectiveness in learning with unlabeled data. Most of existing method…
3D Siamese Transformer Network for Single Object Tracking on Point Clouds
Le Hui, Lingpeng Wang, Linghua Tang +3
Siamese network based trackers formulate 3D single object tracking as cross-correlation learning between point features of a template and a search area. Due to the large appearance…
RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation
Mu He, Le Hui, Yikai Bian +3
Existing self-supervised monocular depth estimation methods can get rid of expensive annotations and achieve promising results. However, these methods suffer from severe performanc…
Unsupervised Visible-light Images Guided Cross-Spectrum Depth Estimation from Dual-Modality Cameras
Yubin Guo, Haobo Jiang, Xinlei Qi +3
Cross-spectrum depth estimation aims to provide a depth map in all illumination conditions with a pair of dual-spectrum images. It is valuable for autonomous vehicle applications w…
Reliable Inlier Evaluation for Unsupervised Point Cloud Registration
Yaqi Shen, Le Hui, Haobo Jiang +2
Unsupervised point cloud registration algorithm usually suffers from the unsatisfied registration precision in the partially overlapping problem due to the lack of effective inlier…
3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds
Le Hui, Lingpeng Wang, Mingmei Cheng +2
3D object tracking in point clouds is still a challenging problem due to the sparsity of LiDAR points in dynamic environments. In this work, we propose a Siamese voxel-to-BEV track…
Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration
Haobo Jiang, Yaqi Shen, Jin Xie +3
In this paper, by modeling the point cloud registration task as a Markov decision process, we propose an end-to-end deep model embedded with the cross-entropy method (CEM) for unsu…
UnDeepLIO: Unsupervised Deep Lidar-Inertial Odometry
Yiming Tu, Jin Xie
Extensive research efforts have been dedicated to deep learning based odometry. Nonetheless, few efforts are made on the unsupervised deep lidar odometry. In this paper, we design…
Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration
Haobo Jiang, Jin Xie, Jianjun Qian +1
Point cloud registration is a fundamental problem in 3D computer vision. In this paper, we cast point cloud registration into a planning problem in reinforcement learning, which ca…
SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering
Yifan Zhao, Le Hui, Jin Xie
Point clouds obtained from 3D sensors are usually sparse. Existing methods mainly focus on upsampling sparse point clouds in a supervised manner by using dense ground truth point c…