217 citations · 687 across the 55 of their papers we have counts for
30 papers · 1 filter
GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer
Zheng Qin, Hao Yu, Changjian Wang +5
We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods have shown great potential through bypassing the detection of…
Edge Preserving Implicit Surface Representation of Point Clouds
Xiaogang Wang, Yuhang Cheng, Liang Wang +3
Learning implicit surface directly from raw data recently has become a very attractive representation method for 3D reconstruction tasks due to its excellent performance. However,…
3DRM:Pair-wise relation module for 3D object detection
Yuqing Lan, Yao Duan, Yifei Shi +2
Context has proven to be one of the most important factors in object layout reasoning for 3D scene understanding. Existing deep contextual models either learn holistic features for…
Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision
Yan Liu, Qingyong Hu, Yinjie Lei +3
Learning dense point-wise semantics from unstructured 3D point clouds with fewer labels, although a realistic problem, has been under-explored in literature. While existing weakly…
RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures
Chengjie Niu, Manyi Li, Kai Xu +1
We introduce RIM-Net, a neural network which learns recursive implicit fields for unsupervised inference of hierarchical shape structures. Our network recursively decomposes an inp…
ROSEFusion: Random Optimization for Online Dense Reconstruction under Fast Camera Motion
Jiazhao Zhang, Chenyang Zhu, Lintao Zheng +1
Online reconstruction based on RGB-D sequences has thus far been restrained to relatively slow camera motions (<1m/s). Under very fast camera motion (e.g., 3m/s), the reconstructio…
Potential Convolution: Embedding Point Clouds into Potential Fields
Dengsheng Chen, Haowen Deng, Jun Li +3
Recently, various convolutions based on continuous or discrete kernels for point cloud processing have been widely studied, and achieve impressive performance in many applications,…
StablePose: Learning 6D Object Poses from Geometrically Stable Patches
Yifei Shi, Junwen Huang, Xin Xu +2
We introduce the concept of geometric stability to the problem of 6D object pose estimation and propose to learn pose inference based on geometrically stable patches extracted from…
Learning Fine-Grained Segmentation of 3D Shapes without Part Labels
Xiaogang Wang, Xun Sun, Xinyu Cao +2
Learning-based 3D shape segmentation is usually formulated as a semantic labeling problem, assuming that all parts of training shapes are annotated with a given set of tags. This a…
Hausdorff Point Convolution with Geometric Priors
Pengdi Huang, Liqiang Lin, Fuyou Xue +3
Without a shape-aware response, it is hard to characterize the 3D geometry of a point cloud efficiently with a compact set of kernels. In this paper, we advocate the use of Hausdor…
On Learning the Right Attention Point for Feature Enhancement
Liqiang Lin, Pengdi Huang, Chi-Wing Fu +3
We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e.g., classification and segmentation. Unlike prior works, which wer…
SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images
Yifei Shi, Junwen Huang, Hongjia Zhang +3
We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severely missing data renders geometric detection approach infeasible. We propose an en…
PIE-NET: Parametric Inference of Point Cloud Edges
Xiaogang Wang, Yuelang Xu, Kai Xu +4
We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data. We represent these edges as a collection of parametric curves (i.e.,lines,…
MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
Qian Xie, Yu-Kun Lai, Jing Wu +4
In this paper, we address the 3D object detection task by capturing multi-level contextual information with the self-attention mechanism and multi-scale feature fusion. Most existi…
Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation
Dengsheng Chen, Jun Li, Zheng Wang +1
We present a novel approach to category-level 6D object pose and size estimation. To tackle intra-class shape variations, we learn canonical shape space (CASS), a unified represent…
Constructing the F-Graph with a Symmetric Constraint for Subspace Clustering
Kai Xu, Xiao-Jun Wu, Wen-Bo Hu
Based on further studying the low-rank subspace clustering (LRSC) and L2-graph subspace clustering algorithms, we propose a F-graph subspace clustering algorithm with a symmetric c…
Decoupling Features and Coordinates for Few-shot RGB Relocalization
Siyan Dong, Songyin Wu, Yixin Zhuang +3
Cross-scene model adaption is crucial for camera relocalization in real scenarios. It is often preferable that a pre-learned model can be fast adapted to a novel scene with as few…
PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes
Rundi Wu, Yixin Zhuang, Kai Xu +2
We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly. The input to our network is a 3D shape segmented into parts, where…
Rescan: Inductive Instance Segmentation for Indoor RGBD Scans
Maciej Halber, Yifei Shi, Kai Xu +1
In depth-sensing applications ranging from home robotics to AR/VR, it will be common to acquire 3D scans of interior spaces repeatedly at sparse time intervals (e.g., as part of re…
Learning Part Generation and Assembly for Structure-aware Shape Synthesis
Jun Li, Chengjie Niu, Kai Xu
Learning powerful deep generative models for 3D shape synthesis is largely hindered by the difficulty in ensuring plausibility encompassing correct topology and reasonable geometry…
Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction
Yifei Shi, Angel Xuan Chang, Zhelun Wu +2
Indoor scenes exhibit rich hierarchical structure in 3D object layouts. Many tasks in 3D scene understanding can benefit from reasoning jointly about the hierarchical context of a…
Spatiotemporal CNN for Video Object Segmentation
Kai Xu, Longyin Wen, Guorong Li +2
In this paper, we present a unified, end-to-end trainable spatiotemporal CNN model for VOS, which consists of two branches, i.e., the temporal coherence branch and the spatial segm…
Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes
Xiaogang Wang, Bin Zhou, Yahao Shi +3
For the task of mobility analysis of 3D shapes, we propose joint analysis for simultaneous motion part segmentation and motion attribute estimation, taking a single 3D model as inp…
AdaCoSeg: Adaptive Shape Co-Segmentation with Group Consistency Loss
Chenyang Zhu, Kai Xu, Siddhartha Chaudhuri +3
We introduce AdaCoSeg, a deep neural network architecture for adaptive co-segmentation of a set of 3D shapes represented as point clouds. Differently from the familiar single-insta…