PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

OpenMMLab Pose Estimation Toolbox and Benchmark.

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Point cloud diffusion for 3D model synthesis

Infinite Photorealistic Worlds using Procedural Generation

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

Statistical learning methods, 统计学习方法(第2版)[李航] [笔记, 代码, notebook, 参考文献, Errata, lihang]

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Towards Human-Sounding Speech

Solve Visual Understanding with Reinforced VLMs

High-resolution models for human tasks.

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

Make human motion capture easier.

Official DeiT repository

The simplest, fastest repository for training/finetuning small-sized VLMs.

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

Efficient 3D human pose estimation in video using 2D keypoint trajectories

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

OpenMMLab Pre-training Toolbox and Benchmark

SOTA Re-identification Methods and Toolbox

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

A deep learning library for video understanding research.

Visual tracking library based on PyTorch.