dmarx

cka_pytorch

Reproducing Raghu et al 2021 - Do Vision Transformers See Like Convolutional Neural Networks?

neural-magic-eye

Neural Magic Eye: Learning to See and Understand the Scene Behind an Autostereogram, arXiv:2012.15692.

siren_unofficial

implementation of Sitzmann et al "Implicit Neural Representations with Periodic Activation Functions" - https://arxiv.org/pdf/2006.09661.pdf

3d-photo-inpainting

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

azure-sdk-for-python

This repository is for active development of the Azure SDK for Python. For consumers of the SDK we recommend visiting our public developer docs at https://docs.microsoft.com/en-us/python/azure/ or our versioned developer docs at https://azure.github.io/azure-sdk-for-python.

big-sleep

A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN. Technique was originally created by https://twitter.com/advadnoun

blog

checkin

Simple "diary card" webapp

CleanLawn

Using CV to detect when and where my dog poops in my backyard when unattended.

CLIP-Guided-Diffusion

Just playing with getting CLIP Guided Diffusion running locally, rather than having to use colab.

clip-guided-diffusion-1

Generate vibrant and detailed images using only text.

debugger

deep-daze

Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun

differentiable_volumetric_rendering

This repository contains the code for the CVPR 2020 paper "Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision"

make_with_ml

mvsnerf

[ICCV 2021] Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.

nbdev-sandbox

nerfmm

(Arxiv 2021) NeRF--: Neural Radiance Fields Without Known Camera Parameters

nfpa

pi-GAN

pixel2style2pixel

Official Implementation for "Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation" (CVPR 2021) presenting the pixel2style2pixel (pSp) framework

pytorch-notebook

Docker image with Jupyter, Pytorch and CUDA GPUs supports.

RAFT

Real-ESRGAN

Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

rembg-greenscreen

Rembg Video Virtual Green Screen Edition

searchy

Lightweight and performant semantic image search

StyleGAN-nada

umap

Uniform Manifold Approximation and Projection

utils

random stuff I find useful in my workflow

wiki

Personal wiki authored in GFM