ZhenghaoFei

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Grounded-Segment-Anything

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

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

open_clip

An open source implementation of CLIP.

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

mobile-aloha

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

drake

Model-based design and verification for robotics.

UniAD

[CVPR'23 Best Paper Award] Planning-oriented Autonomous Driving

act-plus-plus

Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

recognize-anything

Open-source and strong foundation image recognition models.

releasing-research-code

Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

Painter

Painter & SegGPT Series: Vision Foundation Models from BAAI

Semantic-SAM

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

GLIP

Grounded Language-Image Pre-training

autodistill

Images to inference with no labeling (use foundation models to train supervised models).

aloha

diffusion_policy

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

CVinW_Readings

A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''

Awesome_Prompting_Papers_in_Computer_Vision

A curated list of prompt-based paper in computer vision and vision-language learning.

open_x_embodiment

act

robomimic

robomimic: A Modular Framework for Robot Learning from Demonstration

apriltag_ros

A ROS wrapper of the AprilTag 3 visual fiducial detector

pybboxes

Light weight toolkit for bounding boxes providing conversion between bounding box types and simple computations.

AgileX-Robotics-all-products-user-manuals

terrasentia-dataset

This dataset is intended for the evaluation of visual-based localization and mapping systems in agriculture.

tesse-core

Core components of TESSE to use as a submodule in a Unity project

strawberry-pp-w-r-dataset

This reop contains the dataset of strawberries picking pint, ripeness and weight annotations.

AutoVRL

AutoVRL is an open-source high fidelity simulator for simulation to real-world autonomous ground vehicle deep reinforcement learning research and development.

leafonlysam