[ECCV 2024] Official implementation of the paper "TAPTR: Tracking Any Point with Transformers as Detection"

Implementation of "FoundPose Unseen Object Pose Estimation with Foundation Features", ECCV 2024

[ECCV 2024] Official implementation of the paper "GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Views"

Refine high-quality datasets and visual AI models

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

3D Reconstruction with Spatial Memory

The MAGSAC algorithm for robust model fitting without using an inlier-outlier threshold

The code for ICCV 2023 paper, Adaptive Reordering Sampler with Neurally Guided MAGSAC

An interactive NVIDIA-GPU process viewer and beyond, the one-stop solution for GPU process management.

An extremely fast Python package and project manager, written in Rust.

Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs

⚡ A Fast, Extensible Progress Bar for Python and CLI

Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Visualization kit for BOP benchmark

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

GLOMAP - Global Structured-from-Motion Revisited

Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Source code of CVPR 2024 paper 'FastMAC: Stochastic Spectral Sampling of Correspondence Graph'

Grounding Image Matching in 3D with MASt3R

[ECCV2024 - Oral, Best Paper Award Candidate] SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow

Source code of CVPR 2023 paper

Dense matching library based on PyTorch

Infinite Photorealistic Worlds using Procedural Generation