Stars
VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
[CVPR 2025] "DepthCues: Evaluating Monocular Depth Perception in Large Vision Models", Duolikun Danier, Mehmet Aygün, Changjian Li, Hakan Bilen, Oisin Mac Aodha
[CVPR'25] UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image
Hackable and optimized Transformers building blocks, supporting a composable construction.
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
Code repository for "DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers"
AllTracker is a model for tracking all pixels in a video.
GoTrack: Generic 6DoF Object Pose Refinement and Tracking, CV4MR 2025
SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow, CVPR2025
Fish-like autosuggestions for zsh
[CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations
Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset
A TTS model capable of generating ultra-realistic dialogue in one pass.
PyTorch code and pretrained weights for the UNIC models.
A PyTorch implementation of the paper "EDGS: Eliminating Densification for Efficient Convergence of 3DGS"
Code for "BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation", ICCV 2025.
Python efficient farthest point sampling (FPS) library. Compatible with numpy.
PyTorch implementation of Levenberg-Marquardt training algorithm
[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
[CVPR 2025] Any6D: Model-free 6D Pose Estimation of Novel Objects
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"
[CVPR 2025] "A Distractor-Aware Memory for Visual Object Tracking with SAM2"