Liang Pan

EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents CVPR 2026 PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image CVPR 2026 PureCC: Pure Learning for Text-to-Image Concept Customization CVPR 2026 Scaling Spatial Intelligence with Multimodal Foundation Models CVPR 2026 WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World CVPR 2026 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion CVPR 2025 A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Difficulty Motions ICCV 2025 Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data and Metric Perspectives ICCV 2025 AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation ICLR 2025 Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding WACV 2025 Diff2I2P: Differentiable Image-to-Point Cloud Registration with Diffusion Prior ICCV 2025 DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes ICLR 2025 GauUpdate: New Object Insertion in 3D Gaussian Fields with Consistent Global Illumination ICCV 2025 LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes CVPR 2025 MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space ICCV 2025 MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D CVPR 2025 SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation ICCV 2025 TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization CVPR 2025 4D Contrastive Superflows are Dense 3D Representation Learners ECCV 2024 Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption CVPR 2024 Digital Life Project: Autonomous 3D Characters with Social Intelligence CVPR 2024 Large-Vocabulary 3D Diffusion Model with Transformer ICLR 2024 Multi-Space Alignments Towards Universal LiDAR Segmentation CVPR 2024 DiffMimic: Efficient Motion Mimicking with Differentiable Physics ICLR 2023 EVA3D: Compositional 3D Human Generation from 2D Image Collections ICLR 2023 Generative Diffusion Prior for Unified Image Restoration and Enhancement CVPR 2023 InsActor: Instruction-driven Physics-based Characters NeurIPS 2023 LaserMix for Semi-Supervised LiDAR Semantic Segmentation CVPR 2023 OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation CVPR 2023 ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model ICCV 2023 Robo3D: Towards Robust and Reliable 3D Perception against Corruptions ICCV 2023 Segment Any Point Cloud Sequences by Distilling Vision Foundation Models NeurIPS 2023 SHERF: Generalizable Human NeRF from a Single Image ICCV 2023 TransPillars: Coarse-To-Fine Aggregation for Multi-Frame 3D Object Detection WACV 2023 A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion ICLR 2022 Benchmarking and Analyzing Point Cloud Classification under Corruptions ICML 2022 HuMMan: Multi-modal 4D Human Dataset for Versatile Sensing and Modeling ECCV 2022 Neural MoCon: Neural Motion Control for Physically Plausible Human Motion Capture CVPR 2022 PTTR: Relational 3D Point Cloud Object Tracking With Transformer CVPR 2022 TAda! Temporally-Adaptive Convolutions for Video Understanding ICLR 2022 TCTrack: Temporal Contexts for Aerial Tracking CVPR 2022 Versatile Multi-Modal Pre-Training for Human-Centric Perception CVPR 2022 Balanced Chamfer Distance as a Comprehensive Metric for Point Cloud Completion NeurIPS 2021 CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing ICCV 2021 Garment4D: Garment Reconstruction from Point Cloud Sequences NeurIPS 2021 Unsupervised 3D Shape Completion Through GAN Inversion CVPR 2021 Variational Relational Point Completion Network CVPR 2021