Code beautifier

[ROBIO 2021] Pole-like Objects Mapping and Long-Term Robot Localization in Dynamic Urban Scenarios

[TMECH 2023] Active View Planning for Visual SLAM in Outdoor Environments Based on Continuous Information Modeling

Learning Resources And Links Of Machine Learning（updating）

Official MegEngine implementation of CREStereo(CVPR 2022 Oral).

总结-改进-汇总

A beautiful stack trace pretty printer for C++

C++ API wrapper for displaying shapes and meshes in Rviz

强化学习玩flappy bird

[ICCV 2021] Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.

A Robust LiDAR-Inertial Odometry for Livox LiDAR

PixelNeRF Official Repository

E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation

Instant neural graphics primitives: lightning fast NeRF and more

Direct voxel grid optimization for fast radiance field reconstruction.

Plenoxels: Radiance Fields without Neural Networks

A repo of awesome papers about multi target multi camera tracking

Out-of-the-box Annotation Toolbox

End-to-End Object Detection with Transformers

An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021 Spotlight

Code for CMaskTrack R-CNN (proposed in Occluded Video Instance Segmentation)

SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)

Toolkit of BDD100K Dataset for Heterogeneous Multitask Learning - CVPR 2020 Oral Paper

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

[CVPR 2021] Youtube-VIS 2021 3rd place, [CVPR 2020] winner DAVIS 2020. Code for mask selection based methods.

MaskTrackRCNN for video instance segmentation based on mmdetection

TrackR-CNN baseline method for Multi-Object Tracking and Segmentation (MOTS)

OpenMMLab Detection Toolbox and Benchmark