-
University of Maryland, College Park
-
07:26
(UTC -04:00) - http://xiyichen.github.io
Highlights
- Pro
Stars
[NeurIPS 2024] MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
CoTracker is a model for tracking any point (pixel) on a video.
(CVPR 2023) CelebV-Text: A Large-Scale Facial Text-Video Dataset
Code for paper "Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photo-Realistic Appearance from Multi-View Video"
[NeurIPS 2024] Generalizable and Animatable Gaussian Head Avatar
This repository is the official implementation of DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Cameras.
ArXiv paper Progressive Autoregressive Video Diffusion Models: https://arxiv.org/abs/2410.08151
Official implementation for the SIGGRAPH Asia 2024 paper SPARK: Self-supervised Personalized Real-time Monocular Face Capture
The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
Automate Finding and Fetching Academic Citations
[arXiv 2024] GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting
Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"
[ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
Generative Models by Stability AI
UpFusion: Novel View Diffusion from Unposed Sparse View Observations (ECCV 2024)
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.
Official repo of "Time Reversal Fusion" (ECCV2024)
Official Implementation of "AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction"
[ECCV 2024] Viewpoint Textual Inversion: Discovering Scene Representations and 3D View Control in 2D Diffusion Models
ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild (ECCV2024)
Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"