Stars
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 80+ languages.
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes
Stratified Transformer for 3D Point Cloud Segmentation (CVPR 2022)
nanobind: tiny and efficient C++/Python bindings
Vector Neurons: A General Framework for SO(3)-Equivariant Networks
This repo is expected to help you develop basic research skills, including technical writing, paper reading, presentation, note-taking, etc.
Helper functions and illustrations of coarse label for semantic segmentation
[CVPR2022] Geometric Transformer for Fast and Robust Point Cloud Registration
Papers and Datasets about Point Cloud.
[CVPR 2022, Oral] Learning Partial point cloud matching in Rigid and Deformable scenes
Pytorch framework for doing deep learning on point clouds.
Pytorch implementation of the paper "Large-Scale Historical Watermark Recognition: dataset and a new consistency-based approach"
This repo contains the released version of code and datasets used for our IROS 2021 paper: "Map Compressibility Assessment for LiDAR Registration.
Python scripts to generate the synthetic data for Paris-CARLA-3D dataset
Hydra is a framework for elegantly configuring complex applications
PyTorch implementation of NeurIPS 2021 paper: "CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration"
Bayesian Coherent Point Drift / Domain Elastic Transform
Fully Convolutional Geometric Features: Fast and accurate 3D features for registration and correspondence.
[ACM MM 2022] You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
[ICCV 2021 - Oral] Bootstrap Your Own Correspondences
Implementation for our CVPR 2021 oral paper "PointNetLK Revisited".
Official Repo for the paper "Neighborhood Normalization for Robust Geometric Feature Learning" (CVPR 2021)