2025
PF-LHM: 3D Animatable Avatar Reconstruction from Pose-free Articulated Human Images.
CoRR, June, 2025

LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds.
CoRR, March, 2025

LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024
StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal.
ACM Trans. Graph., December, 2024

MVImgNet2.0: A Larger-scale Dataset of Multi-view Images.
ACM Trans. Graph., December, 2024

MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation.
CoRR, 2024

MulSMo: Multimodal Stylized Motion Generation by Bidirectional Control Flow.
CoRR, 2024

VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model.
CoRR, 2024

High-Fidelity 3D Textured Shapes Generation by Sparse Encoding and Adversarial Decoding.
Proceedings of the Computer Vision - ECCV 2024, 2024

DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors.
Proceedings of the Computer Vision - ECCV 2024, 2024

MVHumanNet: A Large-Scale Dataset of Multi-View Daily Dressing Human Captures.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Scene Segmentation.
CoRR, 2023

REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videos.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

ETHSeg: An Amodel Instance Segmentation Network and a Real-world Dataset for X-Ray Waste Inspection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
Deep Learning-Based Generic Automatic Surface Defect Inspection (ASDI) With Pixelwise Segmentation.
IEEE Trans. Instrum. Meas., 2021

3DCaricShop: A Dataset and a Baseline Method for Single-View 3D Caricature Face Reconstruction.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

2020
Densely connected GCN model for motion prediction.
Comput. Animat. Virtual Worlds, 2020

Peeking into Occluded Joints: A Novel Framework for Crowd Pose Estimation.
Proceedings of the Computer Vision - ECCV 2020, 2020

2019
A High-Efficiency Fully Convolutional Networks for Pixel-Wise Surface Defect Detection.
IEEE Access, 2019