Publications: Human3R: Everyone Everywhere All at Once (arXiv, 2025); TTT3R: 3D Reconstruction as Test-Time Training (arXiv, 2025); Easi3R: Estimating Disentangled Motion from DUSt3R Without Training (ICCV, 2025); Feat²GS: Probing Visual Foundation Models with Gaussian Splatting (CVPR, 2025); L2G-NeRF: Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields (CVPR, 2023); UV Volumes for Real-time Rendering of Editable Free-view Human Performance (CVPR, 2023); PROCA: Place Recognition under Occlusion and Changing Appearance via Disentangled Representations (ICRA, 2023); Ha-NeRF😆: Hallucinated Neural Radiance Fields in the Wild (CVPR, 2022).
Research Experience
Currently working closely with Anpei Chen at Inception3D Lab. Previously interned at Tencent AI Lab, working with Xuan Wang.
Education
Ph.D. student at Westlake University and Zhejiang University, supervised by Yuliang Xiu and Gerard Pons-Moll; M.S. from Xi'an Jiaotong University; B.S. from Xiamen University.
Background
Research Interests: Modeling 3D/4D worlds from casually captured real-world images and videos; Specialization: Computer Vision and Graphics.
Miscellany
Personal Interests: Making cool stuff, such as rebuilding Hogwarts from Harry Potter movies or recreating lovely moments in 3D from daily photos.