Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge)

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf

LeGO-LOAM, LIO-SAM, LVI-SAM, FAST-LIO2, Faster-LIO, VoxelMap, R3LIVE, Point-LIO, KISS-ICP, DLO, DLIO, Ada-LIO, PV-LIO, SLAMesh, ImMesh, FAST-LIO-MULTI application and comparison on Gazebo and real-…

A collective list of free APIs

Learning with 3D rotations, a hitchhiker’s guide to SO(3) - ICML 2024

Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 30+ benchmarks

DUSt3R: Geometric 3D Vision Made Easy

Книга "Машинное обучение и анализ данных"

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Fast and simple implementation of RL algorithms, designed to run fully on GPU.

Unified framework for robot learning built on NVIDIA Isaac Sim

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

Universal Monocular Metric Depth Estimation

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

Metric depth estimation from a single image

Code for SPAD : Spatially Aware Multiview Diffusers, CVPR 2024

Toy Gaussian Splatting visualization in Unity

Your image is almost there!

Model to check if image was rotated by 90, 180, 270 degrees.

Code for "Detector-Free Structure from Motion", CVPR 2024

3D Gaussian Splat Editor

Massively Parallel Multiview Stereopsis by Surface Normal Diffusion

llama3 implementation one matrix multiplication at a time

A massively parallel, high-level programming language

Official Implementation of CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects

[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and…

API for Grounding DINO 1.5: IDEA Research's Most Capable Open-World Object Detection Model Series

[CVPR2024 Oral] EscherNet: A Generative Model for Scalable View Synthesis

[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.