🤗 image matching webui

Code of π^3: Permutation-Equivariant Visual Geometry Learning

Imitation Learning; Robotics; Policy; VLA;

These scripts are used to download RealEstate10K dataset.

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

🎓Automatically Update CV Papers Daily using Github Actions

[CVPR2025] LightLoc: Learning Outdoor LiDAR Localization at Light Speed

A public repository for ConDo (AAAI25 accepted)

My resume in LaTeX (template suited for new graduates; 应届生简历模板)

[CVPR 2024 Highlight] LiSA: LiDAR Localization with Semantic Awareness

DUSt3R: Geometric 3D Vision Made Easy

Unified framework for building enterprise RAG pipelines with small, specialized models

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

Visual localization made easy with hloc

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

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

[CVPR2023] SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization

(AAAI 2023) RobustLoc: Robust Camera Pose Regression in Challenging Driving Environments

PyTorch implementation of NetVLAD & Online Hardest Triplet Loss.

This repository implements the TransMatch model for unsupervised deformable image registration, as published in the IEEE TMI journal.