liucsg
Follow
perception
3D LiDAR Object Detection & Tracking using Euclidean Clustering, RANSAC, & Hungarian Algorithm
📐A collection of line segments detection algorithms.
A computer vision system was built to detect objects in an indoor scene using point clouds using a deep learning approach. PyTorch was used to implement QI et al’s state of the art, end to end obje…
Open source code for the paper of Neural Sparse Voxel Fields.
Unified Line Segment Detection
[NeurIPS'21] Shape As Points: A Differentiable Poisson Solver
🛣️ automatic extraction of road markings from MLS or ALS point cloud [ISPRS-A' 19]
Multi-Object Tracking via DeepSORT
[CVPR2021] Invertible Image Signal Processing
BARF: Bundle-Adjusting Neural Radiance Fields 🤮 (ICCV 2021 oral)
A ROS package that extracts line segments from LaserScan messages.
A review of change detection methods, including codes and open data sets for deep learning. From paper: change detection based on artificial intelligence: state-of-the-art and challenges.
Algorithms and Publications on 3D Object Tracking
CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection
SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
[PyTorch] Official implementation of CVPR2022 paper "TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers". https://arxiv.org/abs/2203.11496
[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.
Official page of Struct-MDC (RA-L'22 with IROS'22); Depth completion from Visual-SLAM using point & line features
A ROS package for LiDAR's Bird's Eye View projection.
"A case for using rotation invariant features in state of the art feature matchers", CVPRW 2022
SOTA fast and robust ground segmentation using 3D point cloud (accepted in RA-L'21 w/ IROS'21)
[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation （CVPR2022）