Liang Pan

EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents

arXiv 2026

PureCC: Pure Learning for Text-to-Image Concept Customization

arXiv 2026

HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions

arXiv 2026

Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives

ICCV 2025

Scaling Spatial Intelligence with Multimodal Foundation Models

arXiv 2025

PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image

arXiv 2025

3D and 4D World Modeling: A Survey

arXiv 2025

4DNeX: Feed-Forward 4D Generative Modeling Made Easy

arXiv 2025

MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

ICCV 2025

MOSPA: Human Motion Generation Driven by Spatial Audio

arXiv 2025

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

CVPR 2025 1

LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes

CVPR 2025 1

DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes

arXiv 2024

3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors

arXiv 2024

MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D

CVPR 2025 1

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion

CVPR 2025 1

4D Contrastive Superflows are Dense 3D Representation Learners

arXiv 2024

OVGaussian: Generalizable 3D Gaussian Segmentation with Open Vocabularies

arXiv 2024

DreamGaussian4D: Generative 4D Gaussian Splatting

arXiv 2023

SHERF: Generalizable Human NeRF from a Single Image

ICCV 2023 1

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

NeurIPS 2023 11

ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model

ICCV 2023 1

MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model

arXiv 2022

EVA3D: Compositional 3D Human Generation from 2D Image Collections

arXiv 2022

Benchmarking and Analyzing Point Cloud Classification under Corruptions

arXiv 2022

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

CVPR 2023 1