shanjiayao's repositories
ACNet
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
BAT
The official implementation of ICCV paper "Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds".
ByteTrack
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
CUDA-PointPillars
A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.
fastreg
Fast and Robust Registration of Partially Overlapping Point Clouds in Driving Applications
Hierarchical-Localization
Visual localization made easy with hloc
ICCVW21-LiDAR-Panoptic-Segmentation-TradiCV-Survey-of-Point-Cloud-Cluster
A hybrid SOTA solution of LiDAR panoptic segmentation with C++ implementations of point cloud clustering algorithms. ICCV21, Workshop on Traditional Computer Vision in the Age of Deep Learning
linefit_ground_segmentation
Ground Segmentation
M2DGR
M2DGR: a Multi-modal and Multi-scenario Dataset for Ground Robots
Neural_Scene_Flow_Prior
Neural Scene Flow Prior (NeurIPS 2021 spotlight)
nobelium
A static blog build on top of Notion and NextJS, deployed on Vercel.
OpenPCDet
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
Point-Spatio-Temporal-Convolution
Implementation of the "PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences" paper.
PointPillars_MultiHead_40FPS
A REAL-TIME 3D detection network [Pointpillars] compiled by CUDA/TensorRT/C++.
PSTNet2
Implementation of the "Deep Hierarchical Representation of Point Cloud Videos via Spatio-Temporal Decomposition" paper.
PythonRobotics
Python sample codes for robotics algorithms.
pytorch-optimizer
torch-optimizer -- collection of optimizers for Pytorch
Rigid3DSceneFlow
[CVPR 2021, Oral] "Weakly Supervised Learning of Rigid 3D Scene Flow"
sampling-free
Is heuristic sampling necessary in training deep object detectors? Try sampling-free object detectors!
shanjiayao.github.io
This repo is created for my blog
swift-algorithm-club
Algorithms and data structures in Swift, with explanations!
viewer
ML models and internal tensors 3D visualizer
yolov5
YOLOv5 in PyTorch > ONNX > CoreML > TFLite