CoTracker is a model for tracking any point (pixel) on a video.

Cross-platform, customizable ML solutions for live and streaming media.

软件工程常用文档模板及示例：可行性分析报告、开发计划、需求分析文档、概要设计文档、详细设计文档、用户操作手册、测试计划、测试分析报告、开发进度报告、项目开发总结报告、软件维护手册等

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"

Let your Claude able to think

HAnd Gesture Recognition Image Dataset

[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

Intel realsense Depth camera compitable python package for 6 DOF pose estimation

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

[CVPR2024] Code for "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation".

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Efficient neural feature detector and descriptor

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

SceneTracker: Long-term Scene Flow Estimation Network

[CVPR 2024 - Oral] Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

Visual Odometry with Inertial and Depth (VOID) dataset

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

[CVPR 2024 Highlight] Official PyTorch implementation of SpatialTracker: Tracking Any 2D Pixels in 3D Space

Tracking Any Point (TAP)

A PyTorch Implementation of Density Estimation Using Real NVP

Official implementation of AnimateDiff.

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

A procedural Blender pipeline for photorealistic training image generation

[CoRL 2024] Im2Flow2Act: Flow as the Cross-domain Manipulation Interface