Search Results for author:
Found 55 papers, 24 papers with code
A Unified Framework for Human-centric Point Cloud Video Understanding
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.
LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment
Language-guided scene-aware human motion generation has great significance for entertainment and robotics.
HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes
Human-centric 3D scene understanding has recently drawn increasing attention, driven by its critical impact on robotics.
OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries
Occupancy prediction has increasingly garnered attention in recent years for its fine-grained understanding of 3D scenes.
Learning to Adapt SAM for Segmenting Cross-domain Point Clouds
Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data.
Model2Scene: Learning 3D Scene Representation via Contrastive Language-CAD Models Pre-training
In this paper, we propose Model2Scene, a novel paradigm that learns free 3D scene representation from Computer-Aided Design (CAD) models and languages.
Cross-modal and Cross-domain Knowledge Transfer for Label-free 3D Segmentation
Current state-of-the-art point cloud-based perception methods usually rely on large-scale labeled data, which requires expensive manual annotations.
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase
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)
PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection
Recently, polar-based representation has shown promising properties in perceptual tasks.
Human-centric Scene Understanding for 3D Large-scale Scenarios
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.
See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data
They typically align visual features with semantic features obtained from word embedding by the supervision of seen classes' annotations.
Towards Label-free Scene Understanding by Vision Foundation Models
For nuImages and nuScenes datasets, the performance is 22. 1\% and 26. 8\% with improvements of 3. 5\% and 6. 0\%, respectively.
ContrastMotion: Self-supervised Scene Motion Learning for Large-Scale LiDAR Point Clouds
In this paper, we propose a novel self-supervised motion estimator for LiDAR-based autonomous driving via BEV representation.
WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language
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.
One Training for Multiple Deployments: Polar-based Adaptive BEV Perception for Autonomous Driving
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.
SCPNet: Semantic Scene Completion on Point Cloud
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
Rethinking Range View Representation for LiDAR Segmentation
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
CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP
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.
CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection
Second, we present Temporal Motion Alignment module to utilize motion features in sequential frames of data to match two domains.
Zero-shot point cloud segmentation by transferring geometric primitives
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.
Rethinking Trajectory Prediction via "Team Game"
To accurately predict trajectories in multi-agent settings, e. g. team games, it is important to effectively model the interactions among agents.
GANet: Goal Area Network for Motion Forecasting
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
Vision-Centric BEV Perception: A Survey
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.
MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones
In this technical report, we present our solution, dubbed MV-FCOS3D++, for the Camera-Only 3D Detection track in Waymo Open Dataset Challenge 2022.
Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation
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)
STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes
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.
TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers
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
Towards 3D Scene Understanding by Referring Synthetic Models
Promising performance has been achieved for visual perception on the point cloud.
Self-supervised Point Cloud Completion on Real Traffic Scenes via Scene-concerned Bottom-up Mechanism
In this paper, we propose a self-supervised point cloud completion method (TraPCC) for vehicles in real traffic scenes without any complete data.
LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Network
In this work, we address the task of LiDAR-based panoptic segmentation, which aims to parse both objects and scenes in a unified manner.
AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach
Compared to previous methods, our AdaStereo realizes a more standard, complete and effective domain adaptation pipeline.
Referring Self-supervised Learning on 3D Point Cloud
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.
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception
In this paper, we benchmark our model on these three tasks.
SIDE: Center-based Stereo 3D Detector with Structure-aware Instance Depth Estimation
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.
LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation
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).
Probabilistic and Geometric Depth: Detecting Objects in Perspective
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
FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
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
Input-Output Balanced Framework for Long-tailed LiDAR Semantic Segmentation
A thorough and holistic scene understanding is crucial for autonomous vehicles, where LiDAR semantic segmentation plays an indispensable role.
LiDAR-based Panoptic Segmentation via Dynamic Shifting Network
2) Dynamic Shifting for complex point distributions.
Ranked #2 on
Panoptic Segmentation
on SemanticKITTI
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
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
SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks
To suit our network to self-supervised learning, we design several novel loss functions that utilize the inherent properties of LiDAR point clouds.
Channel-wise Alignment for Adaptive Object Detection
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.
Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation
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
Tensor Low-Rank Reconstruction for Semantic Segmentation
Then we use these rank-1 tensors to recover the high-rank context features through our proposed tensor reconstruction module (TRM).
AutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic Points
Then we aggregate dynamic points to instance points, which stand for moving objects such as pedestrians in videos.
AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching
Compared to previous methods for adaptive stereo matching, our AdaStereo realizes a more standard, complete and effective domain adaptation pipeline.
SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds
Multi-class 3D object detection aims to localize and classify objects of multiple categories from point clouds.
Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds
LiDAR is an important method for autonomous driving systems to sense the environment.
Adversarial Attacks on Monocular Depth Estimation
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.
Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints
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.
Adapting Object Detectors via Selective Cross-Domain Alignment
State-of-the-art object detectors are usually trained on public datasets.
TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents
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
Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation
Due to the expensive and time-consuming annotations (e. g., segmentation) for real-world images, recent works in computer vision resort to synthetic data.
Generative Adversarial Frontal View to Bird View Synthesis
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.
Pose Guided Human Video Generation
Human pose, on the other hand, can represent motion patterns intrinsically and interpretably, and impose the geometric constraints regardless of appearance.
