[ICCV 2023] SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection

Official PyTorch implementation of FocalFormer3D [ICCV 2023]

[PyTorch] Official implementation of CVPR2022 paper "TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers". https://arxiv.org/abs/2203.11496

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

Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion (CVPR 2022, Oral)

Focal Sparse Convolutional Networks for 3D Object Detection (CVPR 2022, Oral)

Lingvo

A Simple PointPillars PyTorch Implementation for 3D LiDAR(KITTI) Detection.

A frustum-based method for detecting far-away objects in autonomous driving.

EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection (TPAMI-2022)

CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection

EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection(ECCV 2020)

[ECCV 2020] This is the official implementation of 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection

Implementation of the Multi-Task Multi-Sensor Fusion for 3D Object Detection paper by Uber

code for 3D object detector MLOD

The PyTorch Implementation of F-ConvNet for 3D Object Detection

The papers in this list are about 3d detection, especially those using point clouds.

Papers, code and datasets about deep learning for 3D Object Detection.

Code for 3D object detection for autonomous driving

Unofficial implementation of PointFusion for 3D object bounding box prediction

Robocentric Visual-Inertial Odometry

This repository contains the source code and example output of priority based scheduler

This repository converts 2D occupancy grid into a quad tree and implements planning algorithms for mobile robots using quad tree. Planning works much faster on these because each square represents …

Multi-view 3D Models from Single Images with a Convolutional Network

Reproduce the MV3D network

Multi-View 3D Object Detection Network for Autonomous Driving

This is the stress-ng upstream project git repository. stress-ng will stress test a computer system in various selectable ways. It was designed to exercise various physical subsystems of a computer…

The REBOTNIX RB-Load is a multi-parallel thread application designed for stress testing NVIDIA SoCs (System on Chip).

100 FPS @ 1W Dense Optical flow For Tiny Mobile Robots RAL-2024