Self-hosted AI workspace.

Pytorch implementation of the ECCV 2016 paper "Stacked Hourglass Networks for Human Pose Estimation"

C++ implementation of a ScienceDirect paper "An accelerating cpu-based correlation-based image alignment for real-time automatic optical inspection"

🚩 FastImage, performant React Native image component.

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Spine 3d reconstruction from biplanar images

Fundamental Matrix Estimation with RANSAC

Scalable Image Analysis and Shape Modelling

Official DeiT repository

xLSTM as Generic Vision Backbone

A package for working with whole-slide data including a fast batch iterator that can be used to train deep learning models.

An Agnostic Computer Vision Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come

Simple library for preprocessing histopathological whole-slide images (WSI) into tiles (a.k.a. patches) towards deep learning

tomographic image reconstruction

Python + Octave code for measuring surface height using fringe deflectometry. Probably not useful to anyone else at this point.

Path-RAG: Knowledge-Guided Key Region Retrieval for Open-ended Pathology Visual Question Answering

A TTS model capable of generating ultra-realistic dialogue in one pass.

Graphs for Everyone

Build resilient agents.

The LLM Evaluation Framework

Metrics to evaluate the quality of responses of your Retrieval Augmented Generation (RAG) applications.

An extremely fast Python package and project manager, written in Rust.

A post-processing tool for scanned sheets of paper.

pgvector support for Python

Point cloud diffusion for 3D model synthesis

A 3D Slicer extension for SPECT reconstruction, built using PyTomography

This repository enables easy and fast medical image reconstruction in Python.

Operator Discretization Library https://odl.readthedocs.io/

Perspective Projection-Based 3D CT Reconstruction from Biplanar X-rays (ICASSP 2023, Best Student Paper Awards)