Lists (31)
books
Calibration
cpp
Dataset
DenseReconstruction
DepthEstimation
Feature&Matching
hdmap/vecmap
ImageEnhance
ImagePreprocessing
ImageRetrieval
LLM/VLM
Localization
MVS
Nerf/GS
OpticalFlow
Paper
Perception
ProgramLanguage
python
python_tools
RL
SfM/SLAM
SurfaceReconstruction
Tools
Tracking
tutorial
Vectorization
VIO
Visualization
VO
Stars
Maple Mono: Open source monospace font with round corner, ligatures and Nerd-Font icons for IDE and terminal, fine-grained customization options. 带连字和控制台图标的圆角等宽字体，中英文宽度完美2:1，细粒度的自定义选项
[NeurIPS 2024] An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes
An image retrieval model for any localization task
VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold
[CVPR 2025] JamMa is a lightweight image matcher that enables fast internal and mutual interaction of images with joint Mamba.
Source code of PivotNet (ICCV2023, PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction)
A general map auto annotation framework based on MapTR, with high flexibility in terms of spatial scale and element type
The simplest, fastest repository for training/finetuning small-sized VLMs.
Code for "LiftFeat: 3D Geometry-Aware Local Feature Matching", ICRA2025
A fast and simple structure from motion pipeline written in Pytorch.
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA/Tensor Cores Kernels, HGEMM, FA-2 MMA.🎉
Repository for running the VGGT model in PyTorch
Build, evaluate and run General Multi-Agent Assistance with ease
AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibration (ICCV 2025)
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Modeling, training, eval, and inference code for OLMo
[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
This is the official repository for The Hundred-Page Language Models Book by Andriy Burkov
The Next Step Forward in Multimodal LLM Alignment
Eagle Family: Exploring Model Designs, Data Recipes and Training Strategies for Frontier-Class Multimodal LLMs
Official Repository of paper OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
Textbook on reinforcement learning from human feedback
[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors