All Algorithms implemented in Python

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

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Official implementation of AnimateDiff.

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version

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

Use commands in English to control Blender with OpenAI's GPT-4

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"

A procedural Blender pipeline for photorealistic training image generation

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

Grounded Language-Image Pre-training

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

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

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

Set-of-Mark Prompting for GPT-4V and LMMs

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

[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.

HAnd Gesture Recognition Image Dataset

VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models

Baseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020)

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

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

Kalman Filter implementation in Python using Numpy only in 30 lines.

Toolbox for our GraspNet-1Billion dataset.

A Benchmark Dataset for Apple Detection and Segmentation

SceneTracker: Long-term Scene Flow Estimation Network

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