Jetson Nano C++ implementation of the segformer model.

This repository provides an overview of Segformer, architecture encoder in particular. Some details of Segformer can be misleaded, thus makes a short description here to help understand the model. …

This is the official repo of Panoptic SegFormer [CVPR'22]

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

cuCIM - RAPIDS GPU-accelerated image processing library

You Only Look Once for Panopitic Driving Perception.（MIR2022）

Lightweight Llama 3 8B Inference Engine in CUDA C

Auto-labeling of point cloud sequences for 3D object detection using an ensemble of experts and temporal refinement

Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. C…

OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.

tiny vision language model

GussianPretrain for Visual Pre-training in Autonomous Driving, showcasing significant improvements across various 3D perception tasks, including 3D object detection, HD-map construction, and Occupa…

A tool to download waymo open dataset (https://github.com/waymo-research/waymo-open-dataset) and convert it from TFrecord to general format

国内首个占据栅格网络全栈课程《从BEV到Occupancy Network，算法原理与工程实践》，包含端侧部署。Surrounding Semantic Occupancy Perception Course for Autonomous Driving (docs, ppt and source code) 在线课程主页：http://111.229.117.200:8100/ (作者独立搭建)

Code for a series of work in LiDAR perception, including SST (CVPR 22), FSD (NeurIPS 22), FSD++ (TPAMI 23), FSDv2, and CTRL (ICCV 23, oral).

[ECCV 2022] ST-P3, an end-to-end vision-based autonomous driving framework via spatial-temporal feature learning.

This is the offical implementation of the paper "MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving"

[CVPR2023] Official Implementation of "DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets"

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer

Implemented BEVFormer support for BEV segmentation

A Simple Baseline for BEV Perception

End-to-End Vectorized Autonomous Driving via Probabilistic Planning

[ECCV 2024] The official implementation of DualBEV

Vision-Centric BEV Perception: A Survey

Offical PyTorch implementation of "BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework"