Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

📚 从零开始的大语言模型原理与实践教程

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

An open source code repository of driving world models, with training, inferencing, evaluation tools, and pretrained checkpoints.

[CVPR 2025] ReconDreamer

OpenMMLab's next-generation platform for general 3D object detection.

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

OpenMMLab Rotated Object Detection Toolbox and Benchmark

Depth and Flow for Visual Odometry

SC-Depth (V1, V2, and V3) for Unsupervised Monocular Depth Estimation Webpage:https://jiawangbian.github.io/sc_depth_pl/

Filament is a real-time physically based rendering engine for Android, iOS, Windows, Linux, macOS, and WebGL2

A modular PyTorch library for optical flow estimation using neural networks

Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities

End-to-end SFM framework based on GTSAM

Visual Inertial Odometry with SLAM capabilities and 3D Mesh generation.

Learning Continuous Signed Distance Functions for Shape Representation

This package provides localization in a pre-built map using ICP and odometry (or the IMU measurements).