Zheng Qin

GeoTransformer. [CVPR2022] Geometric Transformer for Fast and Robust Point Cloud Registration

vision3d. Vision3D: A 3D Vision Library built with PyTorch

GraphSCNet. [CVPR2023] Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration

Easy-KPConv. A more easy-to-use implementation of KPConv

FD-MobileNet. This repo contains code for *FD-MobileNet: Improved MobileNet with A Fast Downsampling Strategy*.

diagonalwise-refactorization-caffe. Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions (in Caffe)

diagonalwise-refactorization-pytorch. Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions (in PyTorch)

CNN-Calculator. A simple calculator for computing the number of parameters and FLOPs in convolutional neural networks with PyTorch-like APIs.

ThunderNet. [ICCV2019] ThunderNet: Towards Real-time Generic Object Detection on Mobile Devices

MENet. This repo contains code for *Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications*.

vision3d-engine. Vision3d-Engine: An Easy-to-use yet Powerful Training Engine from Vision3d

diagonalwise-refactorization-tensorflow. Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions (in TensorFlow)

CasViGE. [GMC2023] CasViGE: Learning Robust Point Cloud Registration with Cascaded Visual-Geometric Encoding

Blueberry. [Vibe-coded] Update yourself with latest paper from arXiv.