agermanidis

Liquid-Warping-GAN

PyTorch implementation of our ICCV 2019 paper: Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis

pix2pixHD-runway

image-super-resolution

Super-scale your images and run experiments with Residual Dense and Adversarial Networks.

DeepPrivacy

DeepPrivacy: A Generative Adversarial Network for Face Anonymization

DenseDepth

High Quality Monocular Depth Estimation via Transfer Learning

face-parsing.PyTorch

Using modified BiSeNet for face parsing in PyTorch

fewshot-face-translation-GAN

Generative adversarial networks integrating modules from FUNIT and SPADE for face-swapping.

DeepLabV3

DeepLabV3 ported to Runway

DensePose

A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body

DeOldify

A Deep Learning based project for colorizing and restoring old images

fast-style-transfer

fast style transfer on your webcam, with pre-trained models at

glow

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

ResNet50-Features

Extracting features from images using a pre-trained ResNet50 network

deeplab-pytorch

PyTorch implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC

Fast-SRGAN

A Single Image Super Resolution GAN that uses a mobile net architecture as a generator.

maskrcnn-benchmark

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

runway-face-aligner

squeezenet

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

3DDFA

RunwayML port of 3DDFA

BigBiGAN

Runway Port of BigBiGAN from the paper "Large Scale Adversarial Representation Learning"

ctrl

Conditional Transformer Language Model for Controllable Generation (https://einstein.ai/presentations/ctrl.pdf)

ESRGAN

ESRGAN in Runway

Human-Segmentation-PyTorch

Human segmentation models, training/inference code, and trained weights, implemented in PyTorch

NeuralSteganography

STEGASURAS: STEGanography via Arithmetic coding and Strong neURAl modelS

SPADE-Tensorflow

Simple Tensorflow implementation of "Semantic Image Synthesis with Spatially-Adaptive Normalization" a.k.a. GauGAN, SPADE (CVPR 2019 Oral)

stargan

Official PyTorch Implementation of StarGAN - CVPR 2018

UGATIT

Official Tensorflow implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation

vae-lagging-encoder

PyTorch implementation of Lagging Inference Networks and Posterior Collapse in Variational Autoencoders

VGG16-Features

yolact

A simple, fully convolutional model for real-time instance segmentation.