Search Results for author: Xidong Peng

Found 5 papers, 2 papers with code

Learning to Adapt SAM for Segmenting Cross-domain Point Clouds

no code implementations13 Oct 2023 Xidong Peng, Runnan Chen, Feng Qiao, Lingdong Kong, Youquan Liu, Tai Wang, Xinge Zhu, Yuexin Ma

Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data.

General Knowledge Image Segmentation +4

WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language

no code implementations12 Apr 2023 Zhenxiang Lin, Xidong Peng, Peishan Cong, Yuenan Hou, Xinge Zhu, Sibei Yang, Yuexin Ma

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 and 3D LiDAR point clouds.

Autonomous Driving Object Localization +1

CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection

1 code implementation1 Dec 2022 Xidong Peng, Xinge Zhu, Yuexin Ma

Second, we present Temporal Motion Alignment module to utilize motion features in sequential frames of data to match two domains.

Pseudo Label Unsupervised Domain Adaptation

STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes

1 code implementation CVPR 2022 Peishan Cong, Xinge Zhu, Feng Qiao, Yiming Ren, Xidong Peng, Yuenan Hou, Lan Xu, Ruigang Yang, Dinesh Manocha, Yuexin Ma

In addition, considering the property of sparse global distribution and density-varying local distribution of pedestrians, we further propose a novel method, Density-aware Hierarchical heatmap Aggregation (DHA), to enhance pedestrian perception in crowded scenes.

Pedestrian Detection Sensor Fusion

SIDE: Center-based Stereo 3D Detector with Structure-aware Instance Depth Estimation

no code implementations22 Aug 2021 Xidong Peng, Xinge Zhu, Tai Wang, Yuexin Ma

Due to the information sparsity of local cost volume, we further introduce match reweighting and structure-aware attention, to make the depth information more concentrated.

Depth Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.