Scholar
Xinhang Liu
Google Scholar ID: E2fTMsMAAAAJ
HKUST
Citations & Impact
Citations
570
H-index
8
i10-index
6
Publications
19
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- Trace Anything: Representing Any Video in 4D via Trajectory Fields (Preprint) – proposed trajectory fields for 4D video representation
- Martian World Models: Controllable Video Synthesis with Physically Accurate 3D Reconstructions (NeurIPS 2025)
- CryoFastAR: Fast Cryo-EM Ab Initio Reconstruction Made Easy (ICCV 2025) – first geometric foundation model for pose prediction from Cryo-EM images
- Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs (ICLR 2025)
- ChatCam: Empowering Camera Control through Conversational AI (NeurIPS 2024)
- Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction (ECCV 2024, also presented at ECCV'24 Wild3D Workshop)
- CryoFormer: Continuous Heterogeneous Cryo-EM Reconstruction using Transformer-based Neural Representations (ECCV'24 NFBCC Workshop, Highlight)
- Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling (CVPR 2024, Highlight, top 2.8% of 11,532 submissions)
- Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation (NeurIPS 2022)
