Stars
Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629
GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)
fabio-sim / LightGlue-ONNX
Forked from cvg/LightGlueONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
Sparse Decentralized Collaborative Simultaneous Localization and Mapping Framework for Multi-Robot Systems
Productive, portable, and performant GPU programming in Python.
MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025)
An Open-source Deep Learning Framework for Visual Place Recognition
《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
A curated list of awesome Visual Place Recognition papers
Training library for local feature detection and matching
[ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images
[CVPR'22] NICE-SLAM: Neural Implicit Scalable Encoding for SLAM
[CVPR 2025 Highlight] Matrix3D: Large Photogrammetry Model All-in-One
[CVPR 2025 Best Paper Award Candidate] VGGT: Visual Geometry Grounded Transformer
Bibliographic list for papers of image matching
FastDVDnet: A Very Fast Deep Video Denoising algorithm
Accurate geometric camera calibration with generic camera models
A simple training-free approach adapting DUSt3R for dynamic scenes.
Optimal Transport Aggregation for Visual Place Recognition
[SIGGRAPH Asia 2024] V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians
On-device AI across mobile, embedded and edge for PyTorch
[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
SpatialLM: Training Large Language Models for Structured Indoor Modeling
PyTorch code and models for the DINOv2 self-supervised learning method.
Official implementation of "ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis"
Official implementation of TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models
An image retrieval model for any localization task