Stars
End-to-End SLAM with camera calibration, monocular prior integration and dense Rendering
GSFusion: Online RGB-D Mapping Where Gaussian Splatting Meets TSDF Fusion
Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"
[arXiv'24] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
Efficient vision foundation models for high-resolution generation and perception.
[ECCV'24] FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information
HunyuanVideo: A Systematic Framework For Large Video Generation Model
No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
DepthSplat: Connecting Gaussian Splatting and Depth
A machine learning framework for reconstructing articulated 3D animals from images
Repository relating to "Reinforcement Learning Meets Visual Odometry" (ECCV, 2024).
run DROID-SLAM with Metric3D to improve monocular performance
code for "DeFlowSLAM: Self-Supervised Scene Motion Decomposition for Dynamic Dense SLAM"
DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Dense Structure from Motion in the Wild
[CoRL '23] Dexterous piano playing with deep reinforcement learning.
Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"
[ECCV 2024] Official Implementation of DragAPart: Learning a Part-Level Motion Prior for Articulated Objects.
(ECCV '24) DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting
[ECCV2024 - Oral, Best Paper Award Candidate] SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow
[CVPR'24] MorpheuS: Neural Dynamic 360° Surface Reconstruction from Monocular RGB-D Video
Official implementation of "ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis"
3DGS-LM accelerates Gaussian-Splatting optimization by replacing the ADAM optimizer with Levenberg-Marquardt.
A Python package for the TartanAir-V2 dataset.
[3DV'25] 3D Reconstruction with Spatial Memory