Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

Demo package for ROS2 that publishes a point cloud and visualizes it using RViz2

See `releases` for binary wheels for ubuntu 16.04

4D Radar Object Detection for Autonomous Driving in Various Weather Conditions

Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"

Go-ICP for globally optimal 3D pointset registration

The repository archives valuable information related to intelligent transportation systems.

[ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering

AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception, CVPR 2022.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Official implementation of the paper "You Only Need Adversarial Supervision for Semantic Image Synthesis" (ICLR 2021)

A library for differentiable robotics on manifolds.

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

Google Drive Public File Downloader when Curl/Wget Fails

[CVPR'23] TARL: Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving

Patchwork++: Fast and robust ground segmentation method for 3D LiDAR scans. @ IROS'22

(T-IV, ITSC) Auto-labeling of point cloud sequences for 3D object detection using an ensemble of experts and temporal refinement

MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences (ICCV 2019 Oral)

Behind the Curtain: Learning Occluded Shapes for 3D Object Detection

PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.

This is a pytorch implementation of k-means clustering algorithm

ONNX-TensorRT: TensorRT backend for ONNX

Reconstruction of the original paper on neural style transfer (Gatys et al.). I've additionally included reconstruction scripts which allow you to reconstruct only the content or the style of the i…

TensorFlow CNN for fast style transfer ⚡🖥🎨🖼

A LiDAR odometry pipeline that just works

Export CenterPoint PonintPillars ONNX Model For TensorRT

NumPy arrays, ready for human consumption

Argoverse 2: Next generation datasets for self-driving perception and forecasting.