Open source impl of **MV-DUSt3R+ Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds** from Meta Reality Labs. Project page https://mv-dust3rp.github.io/

Implementation of Newcombe et al. CVPR 2015 DynamicFusion paper

Uncommon Objects in 3D dataset

Official PyTorch implementation of the paper "Dataset Distillation with Neural Characteristic Function" (NCFM) in CVPR 2025.

[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation

[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

CVPR 2025 论文和开源项目合集

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

Code for "Detector-Free Structure from Motion", CVPR 2024

https://coshand.cs.columbia.edu/

Visual localization made easy with hloc

Grounding Image Matching in 3D with MASt3R

Original reference implementation of "EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis"

Official PyTorch Implementation of "History-Guided Video Diffusion"

Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

[3DV'25] 3D Reconstruction with Spatial Memory

DUSt3R: Geometric 3D Vision Made Easy

Acceptance rates for the major AI conferences

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images

Official implementation for "DMesh++: An Efficient Differentiable Mesh for Complex Shapes".

Official PyTorch Implementation for Task Vectors are Cross-Modal

Gaga: Group Any Gaussians via 3D-aware Memory Bank

(WIP) A small but powerful, homemade PyTorch from scratch.