PyTorch Implementation of PointPillars

Advanced Fast and Accurate 3D Object Detection using ResNet Architecture and Feature Pyramid Networks

Real Time 3D Point Cloud Detection

Graded projects of the course Deep Learning for Autonomous Driving, ETH Zürich (Spring 2021). Topics: Multi-task learning for semantics and depth, 3D Object Detection from Lidar Point Clouds.

PointVoxel-RCNN (PV-RCNN), is a two-stage 3D detection framework aiming at more accurate 3D object detection from point clouds. 3D detection approaches are based on either 3D voxel CNN with sparse convolution or PointNet-based networks as the backbone. 3D voxel CNNs with sparse convolution are more efficient and are able to generate high-quality…

A two stage multi-modal loss model along with rigid body transformations to regress 3D bounding boxes

Some useful functions for working with the KITTI Dataset. Implementation of VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection.

3D Object Detection by Colorful Pointcloud. Alignment Between RGB image and Lidar Pointcloud

Real-Time Hand Gesture-Driven 3D Object Manipulation

Lidar Obstacle Detection using RANSAC, PCA, and KD-tree Cluster

Notes and key takeaways of the Self-Driving Cars Perception applied Deep Learning Free Course from freeCodeCamp.org

Ray Denoising (RayDN): Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection

[IVS'24] UniBEV: the official implementation of UniBEV

Frustum PointNets for 3D Object Detection from RGB-D Data

Implementation of SECOND in PyTorch for KITTI 3D Object Detetcion

Annotation File Converter is a GitHub repository that includes Python-based conversion scripts to convert annotations from one format to another.

Official codebase of HyDRa.

Master Thesis: Weakly Supervised Monocular 3D Object Detection

A repository contained summaries and dissections of recent research papers in computer vision.

ICCV 2021 papers and code focus on point cloud analysis