HMX2013
Follow
3D deep learning
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion (CVPR 2022, Oral)
OpenMMLab Detection Toolbox and Benchmark
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
A 3D computer vision development toolkit based on PaddlePaddle. It supports point-cloud object detection, segmentation, and monocular 3D object detection models.
Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)
OpenMMLab's next-generation platform for general 3D object detection.
[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
GndNet: Fast ground plane estimation and point cloud segmentation for autonomous vehicles using deep neural networks.
(LMNet) Moving Object Segmentation in 3D LiDAR Data: A Learning-based Approach Exploiting Sequential Data (RAL/IROS 2021)
Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)
TensorRT deployment for CenterPoint Lidar Detection Model.
Export CenterPoint PonintPillars ONNX Model For TensorRT
Implementation of SqueezeSeg, convolutional neural networks for LiDAR point clout segmentation
[PyTorch] Official implementation of CVPR2022 paper "TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers". https://arxiv.org/abs/2203.11496
3D detection and tracking viewer (visualization) for kitti & waymo dataset
Convert KITTI dataset to ROS bag file the easy way!
Object detection / tracking / fusion based on Apollo r3.0.0 perception module in ROS
PyTorch code for "Locating objects without bounding boxes" - Loss function and trained models
Tensorflow implementation of Multi-View 3D Object Detection Network (in progress)
Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions (RAL 2022)
Realtime Camera-Radar-Lidar Fusion detection in ROS simulation.
A REAL-TIME 3D detection network [Pointpillars] compiled by CUDA/TensorRT/C++.