Yuexin Ma

41

Papers

392

Total Citations

Papers (41)

GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces

Multi-Space Alignments Towards Universal LiDAR Segmentation

HybridGait: A Benchmark for Spatial-Temporal Cloth-Changing Gait Recognition with Hybrid Explorations

LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment

OccMamba: Semantic Occupancy Prediction with State Space Models

Can LVLMs Obtain a Driver’s License? A Benchmark Towards Reliable AGI for Autonomous Driving

TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation

RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method

SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance

CityAnchor: City-scale 3D Visual Grounding with Multi-modality LLMs

Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis

A Unified Framework for Human-centric Point Cloud Video Understanding

🎧MOSPA: Human Motion Generation Driven by Spatial Audio

FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments

UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis

DexH2R: A Benchmark for Dynamic Dexterous Grasping in Human-to-Robot Handover

EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild

DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness

ClimbingCap: Multi-Modal Dataset and Method for Rock Climbing in World Coordinate

GaussianPro: 3D Gaussian Splatting with Progressive Propagation

ChallenCap: Monocular 3D Capture of Challenging Human Performances Using Multi-Modal References

Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation

Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-View Transformation

ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving

Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation

LiDARCap: Long-Range Marker-Less 3D Human Motion Capture With LiDAR Point Clouds

HSC4D: Human-Centered 4D Scene Capture in Large-Scale Indoor-Outdoor Space Using Wearable IMUs and LiDAR

CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP

SCPNet: Semantic Scene Completion on Point Cloud

SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments

CIMI4D: A Large Multimodal Climbing Motion Dataset Under Human-Scene Interactions

UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase

See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data

Rethinking Range View Representation for LiDAR Segmentation

Human-centric Scene Understanding for 3D Large-scale Scenarios

AutoTrajectory: Label-free Trajectory Extraction and Prediction from Videos using Dynamic Points

STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes

HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes

Towards Label-free Scene Understanding by Vision Foundation Models