Blender add-on for editing scenes reconstructed with SuGaR or Gaussian Frosting.

Pose estimation refiner

A delightful community-driven framework for managing your bash configuration, and an auto-update tool so that makes it easy to keep up with the latest updates from the community.

[Preprint] SADG: Segment Any Dynamic Gaussian Without Object Trackers

Multi-camera calibration using one or more calibration patterns

[ICCV 2023 R6D] PyTorch implementation of CNOS: A Strong Baseline for CAD-based Novel Object Segmentation based on Segmenting Anything and DINOv2

[CVPR 2024] MemFlow: Optical Flow Estimation and Prediction with Memory

Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video” (ECCV 2024)

Prompt, run, edit, and deploy full-stack web applications using any LLM you want!

Lightweight Arduino Simulator

[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation

3D高斯论文，持续更新，欢迎交流讨论。

VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation

Official implementation for the paper CHORE, ECCV'22

Code for the ECCV2020 paper "Shape and Viewpoint without Keypoints".

[CVPR 2024] PyTorch implementation of GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.

Code for "MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare", CoRL 2022.

Code for "OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models" NeurIPS 2022

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022

[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.