no code implementations • 29 Mar 2024 • Yiteng Xu, Kecheng Ye, Xiao Han, Yiming Ren, Xinge Zhu, Yuexin Ma
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 advancing downstream human-centric tasks and applications.
1 code implementation • 20 Mar 2024 • Peishan Cong, Ziyi Wang, Zhiyang Dou, Yiming Ren, Wei Yin, Kai Cheng, Yujing Sun, Xiaoxiao Long, Xinge Zhu, Yuexin Ma
Language-guided scene-aware human motion generation has great significance for entertainment and robotics.
no code implementations • 5 Mar 2024 • Yichen Yao, Zimo Jiang, Yujing Sun, Zhencai Zhu, Xinge Zhu, Runnan Chen, Yuexin Ma
Human-centric 3D scene understanding has recently drawn increasing attention, driven by its critical impact on robotics.
1 code implementation • 6 Dec 2023 • Yuhang Lu, Xinge Zhu, Tai Wang, Yuexin Ma
Occupancy prediction has increasingly garnered attention in recent years for its fine-grained understanding of 3D scenes.
no code implementations • 13 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.
no code implementations • 29 Sep 2023 • Runnan Chen, Xinge Zhu, Nenglun Chen, Dawei Wang, Wei Li, Yuexin Ma, Ruigang Yang, Tongliang Liu, Wenping Wang
In this paper, we propose Model2Scene, a novel paradigm that learns free 3D scene representation from Computer-Aided Design (CAD) models and languages.
no code implementations • 19 Sep 2023 • Jingyu Zhang, Huitong Yang, Dai-Jie Wu, Jacky Keung, Xuesong Li, Xinge Zhu, Yuexin Ma
Current state-of-the-art point cloud-based perception methods usually rely on large-scale labeled data, which requires expensive manual annotations.
1 code implementation • ICCV 2023 • Youquan Liu, Runnan Chen, Xin Li, Lingdong Kong, Yuchen Yang, Zhaoyang Xia, Yeqi Bai, Xinge Zhu, Yuexin Ma, Yikang Li, Yu Qiao, Yuenan Hou
Besides, we construct the OpenPCSeg codebase, which is the largest and most comprehensive outdoor LiDAR segmentation codebase.
Ranked #2 on 3D Semantic Segmentation on SemanticKITTI (using extra training data)
1 code implementation • ICCV 2023 • Ming Nie, Yujing Xue, Chunwei Wang, Chaoqiang Ye, Hang Xu, Xinge Zhu, Qingqiu Huang, Michael Bi Mi, Xinchao Wang, Li Zhang
Recently, polar-based representation has shown promising properties in perceptual tasks.
1 code implementation • ICCV 2023 • Yiteng Xu, Peishan Cong, Yichen Yao, Runnan Chen, Yuenan Hou, Xinge Zhu, Xuming He, Jingyi Yu, Yuexin Ma
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-environment interactions, severe occlusions in crowds, etc.
no code implementations • ICCV 2023 • Yuhang Lu, Qi Jiang, Runnan Chen, Yuenan Hou, Xinge Zhu, Yuexin Ma
They typically align visual features with semantic features obtained from word embedding by the supervision of seen classes' annotations.
1 code implementation • NeurIPS 2023 • Runnan Chen, Youquan Liu, Lingdong Kong, Nenglun Chen, Xinge Zhu, Yuexin Ma, Tongliang Liu, Wenping Wang
For nuImages and nuScenes datasets, the performance is 22. 1\% and 26. 8\% with improvements of 3. 5\% and 6. 0\%, respectively.
no code implementations • 25 Apr 2023 • Xiangze Jia, Hui Zhou, Xinge Zhu, Yandong Guo, Ji Zhang, Yuexin Ma
In this paper, we propose a novel self-supervised motion estimator for LiDAR-based autonomous driving via BEV representation.
no code implementations • 12 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.
no code implementations • 2 Apr 2023 • Huitong Yang, Xuyang Bai, Xinge Zhu, Yuexin Ma
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, costing huge computing resources.
1 code implementation • CVPR 2023 • Zhaoyang Xia, Youquan Liu, Xin Li, Xinge Zhu, Yuexin Ma, Yikang Li, Yuenan Hou, Yu Qiao
We propose a simple yet effective label rectification strategy, which uses off-the-shelf panoptic segmentation labels to remove the traces of dynamic objects in completion labels, greatly improving the performance of deep models especially for those moving objects.
Ranked #1 on 3D Semantic Scene Completion on SemanticKITTI
no code implementations • ICCV 2023 • Lingdong Kong, Youquan Liu, Runnan Chen, Yuexin Ma, Xinge Zhu, Yikang Li, Yuenan Hou, Yu Qiao, Ziwei Liu
We show that, for the first time, a range view method is able to surpass the point, voxel, and multi-view fusion counterparts in the competing LiDAR semantic and panoptic segmentation benchmarks, i. e., SemanticKITTI, nuScenes, and ScribbleKITTI.
Ranked #4 on 3D Semantic Segmentation on SemanticKITTI
1 code implementation • CVPR 2023 • Runnan Chen, Youquan Liu, Lingdong Kong, Xinge Zhu, Yuexin Ma, Yikang Li, Yuenan Hou, Yu Qiao, Wenping Wang
For the first time, our pre-trained network achieves annotation-free 3D semantic segmentation with 20. 8% and 25. 08% mIoU on nuScenes and ScanNet, respectively.
1 code implementation • 1 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.
no code implementations • 18 Oct 2022 • Runnan Chen, Xinge Zhu, Nenglun Chen, Wei Li, Yuexin Ma, Ruigang Yang, Wenping Wang
To this end, we propose a novel framework to learn the geometric primitives shared in seen and unseen categories' objects and employ a fine-grained alignment between language and the learned geometric primitives.
no code implementations • 17 Oct 2022 • Zikai Wei, Xinge Zhu, Bo Dai, Dahua Lin
To accurately predict trajectories in multi-agent settings, e. g. team games, it is important to effectively model the interactions among agents.
1 code implementation • 20 Sep 2022 • Mingkun Wang, Xinge Zhu, Changqian Yu, Wei Li, Yuexin Ma, Ruochun Jin, Xiaoguang Ren, Dongchun Ren, Mingxu Wang, Wenjing Yang
In view of this, we propose a new goal area-based framework, named Goal Area Network (GANet), for motion forecasting, which models goal areas rather than exact goal coordinates as preconditions for trajectory prediction, performing more robustly and accurately.
Ranked #15 on Motion Forecasting on Argoverse CVPR 2020
1 code implementation • 4 Aug 2022 • Yuexin Ma, Tai Wang, Xuyang Bai, Huitong Yang, Yuenan Hou, Yaming Wang, Yu Qiao, Ruigang Yang, Dinesh Manocha, Xinge Zhu
In recent years, vision-centric Bird's Eye View (BEV) perception has garnered significant interest from both industry and academia due to its inherent advantages, such as providing an intuitive representation of the world and being conducive to data fusion.
1 code implementation • 26 Jul 2022 • Tai Wang, Qing Lian, Chenming Zhu, Xinge Zhu, Wenwei Zhang
In this technical report, we present our solution, dubbed MV-FCOS3D++, for the Camera-Only 3D Detection track in Waymo Open Dataset Challenge 2022.
no code implementations • CVPR 2022 • Yuenan Hou, Xinge Zhu, Yuexin Ma, Chen Change Loy, Yikang Li
This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation.
Ranked #8 on LIDAR Semantic Segmentation on nuScenes (val mIoU metric)
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.
1 code implementation • CVPR 2022 • Xuyang Bai, Zeyu Hu, Xinge Zhu, Qingqiu Huang, Yilun Chen, Hongbo Fu, Chiew-Lan Tai
The attention mechanism of the transformer enables our model to adaptively determine where and what information should be taken from the image, leading to a robust and effective fusion strategy.
Ranked #3 on 3D Object Detection on nuScenes LiDAR only
no code implementations • 20 Mar 2022 • Runnan Chen, Xinge Zhu, Nenglun Chen, Dawei Wang, Wei Li, Yuexin Ma, Ruigang Yang, Wenping Wang
Promising performance has been achieved for visual perception on the point cloud.
no code implementations • 20 Mar 2022 • Yiming Ren, Peishan Cong, Xinge Zhu, Yuexin Ma
In this paper, we propose a self-supervised point cloud completion method (TraPCC) for vehicles in real traffic scenes without any complete data.
1 code implementation • 14 Mar 2022 • Fangzhou Hong, Hui Zhou, Xinge Zhu, Hongsheng Li, Ziwei Liu
In this work, we address the task of LiDAR-based panoptic segmentation, which aims to parse both objects and scenes in a unified manner.
no code implementations • 9 Dec 2021 • Xiao Song, Guorun Yang, Xinge Zhu, Hui Zhou, Yuexin Ma, Zhe Wang, Jianping Shi
Compared to previous methods, our AdaStereo realizes a more standard, complete and effective domain adaptation pipeline.
no code implementations • 29 Sep 2021 • Runnan Chen, Xinge Zhu, Nenglun Chen, Dawei Wang, Wei Li, Yuexin Ma, Ruigang Yang, Wenping Wang
In this paper, we study a new problem named Referring Self-supervised Learning (RSL) on 3D scene understanding: Given the 3D synthetic models with labels and the unlabeled 3D real scene scans, our goal is to distinguish the identical semantic objects on an unseen scene according to the referring synthetic 3D models.
1 code implementation • 12 Sep 2021 • Xinge Zhu, Hui Zhou, Tai Wang, Fangzhou Hong, Wei Li, Yuexin Ma, Hongsheng Li, Ruigang Yang, Dahua Lin
In this paper, we benchmark our model on these three tasks.
no code implementations • 22 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.
no code implementations • 17 Aug 2021 • Lin Zhao, Hui Zhou, Xinge Zhu, Xiao Song, Hongsheng Li, Wenbing Tao
However, two major issues of the fusion between camera and LiDAR hinder its performance, \ie, how to effectively fuse these two modalities and how to precisely align them (suffering from the weak spatiotemporal synchronization problem).
1 code implementation • 29 Jul 2021 • Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin
As the preliminary depth estimation of each instance is usually inaccurate in this ill-posed setting, we incorporate a probabilistic representation to capture the uncertainty.
Ranked #10 on 3D Object Detection on KITTI Cars Hard val
8 code implementations • 22 Apr 2021 • Tai Wang, Xinge Zhu, Jiangmiao Pang, Dahua Lin
In this paper, we study this problem with a practice built on a fully convolutional single-stage detector and propose a general framework FCOS3D.
Ranked #323 on 3D Object Detection on nuScenes
no code implementations • 26 Mar 2021 • Peishan Cong, Xinge Zhu, Yuexin Ma
A thorough and holistic scene understanding is crucial for autonomous vehicles, where LiDAR semantic segmentation plays an indispensable role.
1 code implementation • CVPR 2021 • Fangzhou Hong, Hui Zhou, Xinge Zhu, Hongsheng Li, Ziwei Liu
2) Dynamic Shifting for complex point distributions.
Ranked #2 on Panoptic Segmentation on SemanticKITTI
2 code implementations • CVPR 2021 • Xinge Zhu, Hui Zhou, Tai Wang, Fangzhou Hong, Yuexin Ma, Wei Li, Hongsheng Li, Dahua Lin
However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited.
Ranked #2 on 3D Semantic Segmentation on ScribbleKITTI
no code implementations • 19 Oct 2020 • Yan Xu, Zhaoyang Huang, Kwan-Yee Lin, Xinge Zhu, Jianping Shi, Hujun Bao, Guofeng Zhang, Hongsheng Li
To suit our network to self-supervised learning, we design several novel loss functions that utilize the inherent properties of LiDAR point clouds.
no code implementations • 7 Sep 2020 • Hang Yang, Shan Jiang, Xinge Zhu, Mingyang Huang, Zhiqiang Shen, Chunxiao Liu, Jianping Shi
Existing methods on this task usually draw attention on the high-level alignment based on the whole image or object of interest, which naturally, cannot fully utilize the fine-grained channel information.
3 code implementations • 4 Aug 2020 • Hui Zhou, Xinge Zhu, Xiao Song, Yuexin Ma, Zhe Wang, Hongsheng Li, Dahua Lin
A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space.
Ranked #11 on LIDAR Semantic Segmentation on nuScenes
no code implementations • ECCV 2020 • Wanli Chen, Xinge Zhu, Ruoqi Sun, Junjun He, Ruiyu Li, Xiaoyong Shen, Bei Yu
Then we use these rank-1 tensors to recover the high-rank context features through our proposed tensor reconstruction module (TRM).
no code implementations • ECCV 2020 • Yuexin Ma, Xinge ZHU, Xinjing Cheng, Ruigang Yang, Jiming Liu, Dinesh Manocha
Then we aggregate dynamic points to instance points, which stand for moving objects such as pedestrians in videos.
no code implementations • CVPR 2021 • Xiao Song, Guorun Yang, Xinge Zhu, Hui Zhou, Zhe Wang, Jianping Shi
Compared to previous methods for adaptive stereo matching, our AdaStereo realizes a more standard, complete and effective domain adaptation pipeline.
1 code implementation • 6 Apr 2020 • Xinge Zhu, Yuexin Ma, Tai Wang, Yan Xu, Jianping Shi, Dahua Lin
Multi-class 3D object detection aims to localize and classify objects of multiple categories from point clouds.
no code implementations • 6 Apr 2020 • Tai Wang, Xinge Zhu, Dahua Lin
LiDAR is an important method for autonomous driving systems to sense the environment.
no code implementations • 23 Mar 2020 • Ziqi Zhang, Xinge Zhu, Yingwei Li, Xiangqun Chen, Yao Guo
In order to understand the impact of adversarial attacks on depth estimation, we first define a taxonomy of different attack scenarios for depth estimation, including non-targeted attacks, targeted attacks and universal attacks.
no code implementations • ICCV 2019 • Yan Xu, Xinge Zhu, Jianping Shi, Guofeng Zhang, Hujun Bao, Hongsheng Li
Most of existing methods directly train a network to learn a mapping from sparse depth inputs to dense depth maps, which has difficulties in utilizing the 3D geometric constraints and handling the practical sensor noises.
1 code implementation • CVPR 2019 • Xinge Zhu, Jiangmiao Pang, Ceyuan Yang, Jianping Shi, Dahua Lin
State-of-the-art object detectors are usually trained on public datasets.
1 code implementation • 6 Nov 2018 • Yuexin Ma, Xinge Zhu, Sibo Zhang, Ruigang Yang, Wenping Wang, Dinesh Manocha
To safely and efficiently navigate in complex urban traffic, autonomous vehicles must make responsible predictions in relation to surrounding traffic-agents (vehicles, bicycles, pedestrians, etc.).
Ranked #1 on Trajectory Prediction on Apolloscape Trajectory
no code implementations • ECCV 2018 • Xinge Zhu, Hui Zhou, Ceyuan Yang, Jianping Shi, Dahua Lin
Due to the expensive and time-consuming annotations (e. g., segmentation) for real-world images, recent works in computer vision resort to synthetic data.
no code implementations • 1 Aug 2018 • Xinge Zhu, Zhichao Yin, Jianping Shi, Hongsheng Li, Dahua Lin
Due to the large gap and severe deformation between the frontal view and bird view, generating a bird view image from a single frontal view is challenging.
no code implementations • ECCV 2018 • Ceyuan Yang, Zhe Wang, Xinge Zhu, Chen Huang, Jianping Shi, Dahua Lin
Human pose, on the other hand, can represent motion patterns intrinsically and interpretably, and impose the geometric constraints regardless of appearance.