Matthew Allen Fisher's repositories
2dimageto3dmodel
We evaluate our method on different datasets (including ShapeNet, CUB-200-2011, and Pascal3D+) and achieve state-of-the-art results, outperforming all the other supervised and unsupervised methods and 3D representations, all in terms of performance, accuracy, and training time.
arxiv-audio-summaries
Want to get a summary of a new ARXIV paper? Don't even want to read the summary? Have the best read it out loud for you!
gmail-signature
:rabbit: Most elegant looking Gmail Signature in the world :metal:
img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Keyboard-Interface
Made for accepting input from an Impaact GX61, should work for many keyboard
langchain
⚡ Building applications with LLMs through composability ⚡
MagicLeap_CustomComputerVision
Code written to connect a local machine running a Python server to Magic Leap's camera feed to run custom computer vision models. Made for the MIT Reality Virtually Hackathon 2019.
MonaGlyphic
MonaVerse
ranked-aesthetic-scorer
Created as a change to the improved-aesthetic-scorer that allows for using ranked/pairwise datasets to train the aesthetic scorer
react-three-next
React Three Fiber, Nextjs, Tailwind and Styled-components starter
sample-generator
Tools to train a generative model on arbitrary audio samples
stable-diffusion
A latent text-to-image diffusion model
three.js
JavaScript 3D Library.