0iui0

mujoco-2.1-rl-project

Implementing Deep Reinforcement Learning Algorithms in Python for use in the MuJoCo Physics Simulator

MuJoCo-Tutorial

Tutorial on how to get started with MuJoCo Simulation Platform. MuJoCo stands for Multi-Joint dynamics with Contact. It was acquired and made freely available by DeepMind in October 2021, and open sourced in May 2022. Feel free to contribute. Show your support by ✨this repository.

mujoco

Multi-Joint dynamics with Contact. A general purpose physics simulator.

NGD-SLAM

NGD-SLAM: Towards Real-Time SLAM for Dynamic Environments without GPU.

marker

Convert PDF to markdown quickly with high accuracy

ultralytics4channel

Ultralytics 8.2.5 modified to train and predict for 4-channel (RGBD) images.

spoc-robot-training

SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World

3d-bat

3D Bounding Box Annotation Tool (3D-BAT) Point cloud and Image Labeling

fish-speech

Brand new TTS solution

vision-lstm

xLSTM as Generic Vision Backbone

dino-tracker

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

autodistill

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

Depth-Anything-V2

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

BEVSee

[CVPR2024] BEVSee

visualnav-transformer

Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.

ml-4m

4M: Massively Multimodal Masked Modeling

text-prompted-3dgs-segmentation

Unofficial implementation of Segment Anything in 3D Gaussians, with the added functionality of text prompting and multi-view prompt initialization.

InstantSplat

Implementation of InstantSplat where Dust3r is used instead of colmap for points initialization

co-tracker

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

kubric

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

RAFT

MFT

MFT: Long-Term Tracking of Every Pixel -- code for the WACV 2024 paper

pips2

PIPs++

pips

Particle Video Revisited

ATM

Official codebase for "Any-point Trajectory Modeling for Policy Learning"

tapnet

Tracking Any Point (TAP)

Track-2-Act

code for the paper Predicting Point Tracks from Internet Videos enables Diverse Zero-Shot Manipulation

VideoDoodles

Gymnasium

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.