GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or…

Habit Tracker for the AI Coding Workshop

Depth Anything 3

[T-RO 2026] Bundle Adjustment in the Eager Mode

[ECCV 2026] OmniNWM: Omniscient Navigation World Models for Autonomous Driving

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

VGGT implemented in C++

VGGT optimized for VRAM usage - 6x less VRAM, 150 images in 8GB, 1100 images in 32GB

Code and model to control the AH!

[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions

This repository contains a multi-fisheye camera SLAM. The underlying SLAM system is based on ORB-SLAM.

Production-grade 3D gaussian splatting with CPU/GPU support for Windows, Mac and Linux 🚀

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

[T-RO 2025] Scalable Lidar-Visual NeRF

[IJRR 2025] Lidar-visual dataset with ground truth 3D map for SLAM/NeRF

[DEPRECATED] GLOMAP - Global Structured-from-Motion Revisited

Python implementation of Multi-State Constraint Kalman Filter (MSCKF) for Vision-aided Inertial Navigation.

Cylinder and Plane Extraction from Depth Cameras

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

Implementation of CRAFT Text Detection

Fast LOAM: Fast and Optimized Lidar Odometry And Mapping for indoor/outdoor localization IROS 2021

ROS 2 packages for CyberDog

A Robust and Versatile Monocular Visual-Inertial State Estimator

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers. (ICCV 2021 Oral)

CRAFT-Pyotorch：Character Region Awareness for Text Detection Reimplementation for Pytorch

OCR toolbox from Davar-Lab

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021 Spotlight

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-…

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.