Open-source alternatives to Ghostish BAT

0. The CUDA and Pytorch version that is used for this work: ~~~ 'CUDA==10.0', 'torch==1.1.0', 'CUDNN==7.5.0' ~~~ Warning: We tried CUDA11.0+Torch1.7.1 on RTX3090, the AP performance is significantly lower than the aforementioned environment setup.

This repository is for the ICCV 2021 paper NEAT: Neural Attention Fields for End-to-End Autonomous Driving.

By Prarthana Bhattacharyya, Chengjie Huang and Krzysztof Czarnecki.

RTM3D(ECCV2020) and KM3D (namely RTM3D++) are efficiency and accuracy monocular 3D object detection methods for autonomous driving.

Accepted to CVPR2023. 🔥

This is a release of the code of our paper Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds, CVPR 2021.

This is the official implementation of DSGN (CVPR 2020), a strong 3D object detector proposed to jointly estimate scene depth and detect 3D objects in 3D world with only input of a stereo image pair.

Code release for the paper ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection, CVPR 2021 and ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection, T-PAMI 2022.

Mingyu Ding, Yuqi Huo, Hongwei Yi, Zhe Wang, Jianping Shi, Zhiwu Lu, Ping Luo

Pytorch implementation of Depth-conditioned Dynamic Message Propagation forMonocular 3D Object Detection, a paper on CVPR2021.

Garrick Brazil, Xiaoming Liu

Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks(ICCV2021) by Zhihao Liang, Zhihao Li, Songcen Xu, Mingkui Tan, Kui Jia. (\) Corresponding author. [arxiv](https://arxiv.org/abs/2108.07478)…

This is the official repo of 'Weakly Supervised 3D object detection from Lidar Point Cloud' (ECCV2020). Author: Qinghao Meng, Wenguan Wang, Tianfei Zhou, Jianbing Shen, Luc Van Gool, and Dengxin Dai

Hierarchical Aggregation for 3D Instance Segmentation ICCV 2021

Created by Zeyu HU

This is a reproduced repo of "From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to-Point Decoder" (FromVoxelToPoint) and "Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud" (MGAF-3DSSD) in ACM MM 2021.

Jonas Schult 1 , Francis Engelmann 2,3 , Alexander Hermans 1 , Or Litany 4 , Siyu Tang 3 , Bastian Leibe 1

The official implementation of Rank & Sort Loss. Our implementation is based on mmdetection.

In depth-sensing applications ranging from home robotics to AR/VR, it will be common to acquire 3D scans of interior spaces repeatedly at sparse time intervals (e.g., as part of regular daily use). We propose an algorithm that analyzes these ``rescans'' to infer a temporal model of a scene with…

27/04/2023

ECCV 2022 (Oral Presentation)

This repository contains the implementation of CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection.

This repository is the official PyTorch implementation of Active Learning for Deep Object Detection via Probabilistic Modeling, ICCV 2021.

OpenPCDet is a PyTorch deep learning library and toolbox for LiDAR 3D object detection. It functions as a point cloud processing framework designed to develop, train, and evaluate machine learning models that identify and locate objects in three dimensional space. The project includes a GPU-accelerated geometry engine for high-performance implementation of 3D intersection over union and rotated non-maximum suppression. It also provides a distributed model training tool to scale the training and testing of detection models across multiple GPUs and computing nodes. The framework covers point c

World's first general purpose 3D object detection codebse.

Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes