av-processing-1 Goto Github PK

colab_utils

Colab-related code (video to frames, frames to video, youtube video/audio download, preprocessing, ML/DL processing etc)

cyclegan

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

deepupe

Underexposed Photo Enhancement Using Deep Illumination Estimation

depth2time

code for reproducing our interactive art installation "Do silhouettes dream?"

enlightengan

EnlightenGAN: Deep Light Enhancement without Paired Supervision

face-image-motion-model

Face Image Motion Model (Photo-2-Video) based on "first-order-model" repository.

few-shot-adversarial-learning-for-face-swap

This is a unofficial re-implementation of the paper "Few-Shot Adversarial Learning of Realistic Neural Talking Head Models"

funit

Translate images to unseen domains in the test time with few example images.

image-super-resolution

Implementation of Super Resolution CNN in Keras.

mask_rcnn

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

models

Models and examples built with TensorFlow

ngx

Ngx - Neural network based visual generator and mixer

pose-transfer

Code for the paper Progressive Pose Attention for Person Image Generation in CVPR19 (Oral).

pose_transfer_keypoint

pytorch-cyclegan-and-pix2pix

Image-to-image translation in PyTorch (e.g., horse2zebra, edges2cats, and more)

pytorch_gan_zoo

A mix of GAN implementations including progressive growing

sr

Image and video super resolution

stylegan

StyleGAN - Official TensorFlow Implementation

talking-heads

Our implementation of "Few-Shot Adversarial Learning of Realistic Neural Talking Head Models" (Egor Zakharov et al.)

tensorpack

A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

toflow

TOFlow: Video Enhancement with Task-Oriented Flow

vid2vid

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

vid2vid-1

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

videofeedback

Interactive videofeedback VJing software.

vjlxnr

… (one more) simple VJing tool made with max/jitter/m4l …

waifu2x

Image Super-Resolution for Anime-Style Art