Stars
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
Code for MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data
[ECCV 2024] Official Implementation of "Appearance-Based Refinement for Object-Centric Motion Segmentation" Junyu Xie, Weidi Xie, Andrew Zisserman
Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance (CVPR 2024)
[ACCV 2024] Official Implementation of "AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description". Junyu Xie, Tengda Han, Max Bain, Arsha Nagrani, Gül Varol, Weidi Xie, Andrew Zisserman
[ACCV 2024 (Oral)] Official Implementation of "Moving Object Segmentation: All You Need Is SAM (and Flow)" Junyu Xie, Charig Yang, Weidi Xie, Andrew Zisserman
[ECCV 2024] Code for VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models
Gaussian Splatting from VGGSfM and Mast3r, and their comparison
Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
VGGSfM: Visual Geometry Grounded Deep Structure From Motion
Minimal solvers for calibrated camera pose estimation
Lightplane implements a highly memory-efficient differentiable radiance field renderer, and a module for unprojecting features from images to 3D grids.
7th place solution for the Image Matching Challenge 2023.
The repository for paper Unsupervised Volumetric Animation
GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)
[CVPR 2024 - Highlight] FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Official implementation of `Splatter Image: Ultra-Fast Single-View 3D Reconstruction' CVPR 2024