139 citations · 515 across the 57 of their papers we have counts for
55 papers · 1 filter
Registration between Point Cloud Streams and Sequential Bounding Boxes via Gradient Descent
Xuesong Li, Xinge Zhu, Yuexin Ma +2
In this paper, we propose an algorithm for registering sequential bounding boxes with point cloud streams. Unlike popular point cloud registration techniques, the alignment of the…
MCPDepth: Omnidirectional Depth Estimation via Stereo Matching from Multi-Cylindrical Panoramas
Feng Qiao, Zhexiao Xiong, Xinge Zhu +3
Omnidirectional depth estimation presents a significant challenge due to the inherent distortions in panoramic images. Despite notable advancements, the impact of projection method…
StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset
Chaofan Huo, Ye Shi, Yuexin Ma +3
Modeling and capturing the 3D spatial arrangement of the human and the object is the key to perceiving 3D human-object interaction from monocular images. In this work, we propose t…
TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation
Xiaopei Wu, Yuenan Hou, Xiaoshui Huang +8
Training deep models for LiDAR semantic segmentation is challenging due to the inherent sparsity of point clouds. Utilizing temporal data is a natural remedy against the sparsity p…
A Unified Framework for Human-centric Point Cloud Video Understanding
Yiteng Xu, Kecheng Ye, Xiao Han +3
Human-centric Point Cloud Video Understanding (PVU) is an emerging field focused on extracting and interpreting human-related features from sequences of human point clouds, further…
HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes
Yichen Yao, Zimo Jiang, Yujing Sun +4
Human-centric 3D scene understanding has recently drawn increasing attention, driven by its critical impact on robotics. However, human-centric real-life scenarios are extremely di…
OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries
Yuhang Lu, Xinge Zhu, Tai Wang +1
Occupancy prediction has increasingly garnered attention in recent years for its fine-grained understanding of 3D scenes. Traditional approaches typically rely on dense, regular gr…
Cross-modal and Cross-domain Knowledge Transfer for Label-free 3D Segmentation
Jingyu Zhang, Huitong Yang, Dai-Jie Wu +4
Current state-of-the-art point cloud-based perception methods usually rely on large-scale labeled data, which requires expensive manual annotations. A natural option is to explore…
Learning to Adapt SAM for Segmenting Cross-domain Point Clouds
Xidong Peng, Runnan Chen, Feng Qiao +6
Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data. Especial…
Model2Scene: Learning 3D Scene Representation via Contrastive Language-CAD Models Pre-training
Runnan Chen, Xinge Zhu, Nenglun Chen +6
Current successful methods of 3D scene perception rely on the large-scale annotated point cloud, which is tedious and expensive to acquire. In this paper, we propose Model2Scene, a…
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase
Youquan Liu, Runnan Chen, Xin Li +9
Point-, voxel-, and range-views are three representative forms of point clouds. All of them have accurate 3D measurements but lack color and texture information. RGB images are a n…
Human-centric Scene Understanding for 3D Large-scale Scenarios
Yiteng Xu, Peishan Cong, Yichen Yao +6
Human-centric scene understanding is significant for real-world applications, but it is extremely challenging due to the existence of diverse human poses and actions, complex human…
See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data
Yuhang Lu, Qi Jiang, Runnan Chen +3
Zero-shot point cloud segmentation aims to make deep models capable of recognizing novel objects in point cloud that are unseen in the training phase. Recent trends favor the pipel…
Towards Label-free Scene Understanding by Vision Foundation Models
Runnan Chen, Youquan Liu, Lingdong Kong +5
Vision foundation models such as Contrastive Vision-Language Pre-training (CLIP) and Segment Anything (SAM) have demonstrated impressive zero-shot performance on image classificati…
ContrastMotion: Self-supervised Scene Motion Learning for Large-Scale LiDAR Point Clouds
Xiangze Jia, Hui Zhou, Xinge Zhu +3
In this paper, we propose a novel self-supervised motion estimator for LiDAR-based autonomous driving via BEV representation. Different from usually adopted self-supervised strateg…
One Training for Multiple Deployments: Polar-based Adaptive BEV Perception for Autonomous Driving
Huitong Yang, Xuyang Bai, Xinge Zhu +1
Current on-board chips usually have different computing power, which means multiple training processes are needed for adapting the same learning-based algorithm to different chips,…
WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language
Zhenxiang Lin, Xidong Peng, Peishan Cong +6
We introduce the task of 3D visual grounding in large-scale dynamic scenes based on natural linguistic descriptions and online captured multi-modal visual data, including 2D images…
CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions
Ming Yan, Xin Wang, Yudi Dai +5
Motion capture is a long-standing research problem. Although it has been studied for decades, the majority of research focus on ground-based movements such as walking, sitting, dan…
SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments
Yudi Dai, Yitai Lin, Xiping Lin +6
We present SLOPER4D, a novel scene-aware dataset collected in large urban environments to facilitate the research of global human pose estimation (GHPE) with human-scene interactio…
SCPNet: Semantic Scene Completion on Point Cloud
Zhaoyang Xia, Youquan Liu, Xin Li +5
Training deep models for semantic scene completion (SSC) is challenging due to the sparse and incomplete input, a large quantity of objects of diverse scales as well as the inheren…
Rethinking Range View Representation for LiDAR Segmentation
Lingdong Kong, Youquan Liu, Runnan Chen +6
LiDAR segmentation is crucial for autonomous driving perception. Recent trends favor point- or voxel-based methods as they often yield better performance than the traditional range…
IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation
Juze Zhang, Ye Shi, Yuexin Ma +3
This paper presents an inverse kinematic optimization layer (IKOL) for 3D human pose and shape estimation that leverages the strength of both optimization- and regression-based met…
CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP
Runnan Chen, Youquan Liu, Lingdong Kong +6
Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP to help the…
CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection
Xidong Peng, Xinge Zhu, Yuexin Ma
Domain adaptation for Cross-LiDAR 3D detection is challenging due to the large gap on the raw data representation with disparate point densities and point arrangements. By explorin…