Unpaired-Sketch-to-Photo-Translation

We have released our code at https://github.com/rt219/Unsupervised-Sketch-to-Photo-Synthesis

This project is the implementation of Unsupervised Sketch to Photo Synthesis (arxiv: https://arxiv.org/abs/1909.08313).

Photo Generation Examples

This figure shows generated photo images using the proposed model. From left to right: input sketch, generated grayscale photo (shape translation), generated RGB photo (basic colorization), generated RGB photo condition on reference photo (improved colorization), two nearest neighbors of the generated RGB photo. To retrieve the nearest neighbours, we employed an ImageNet pre-trained ResNet18 to extract the deep feature of each image, and computed L2 distance for comparison.

Sketch Generation Examples

This figure shows generated sketch images using the proposed model.

Accumulative Results

This figure shows generated grayscale photo images corresponding to accumulative sketches. The last two images of each example are the final outputs. Accumulative sketches are obtained by manipulating images in SVG format.

An Unpaired Sketch-to-Photo Translation Model

Related tags

Overview

Unpaired-Sketch-to-Photo-Translation

Photo Generation Examples

Sketch Generation Examples

Accumulative Results

Owner

CM building dataset Timisoara

Deep learning toolbox based on PyTorch for hyperspectral data classification.

QICK: Quantum Instrumentation Control Kit

Towards Long-Form Video Understanding

Unofficial implementation of HiFi-GAN+ from the paper "Bandwidth Extension is All You Need" by Su, et al.

The Instructed Glacier Model (IGM)

Code release for Local Light Field Fusion at SIGGRAPH 2019

TrackTech: Real-time tracking of subjects and objects on multiple cameras

This code is 3d-CNN model that can predict environmental value

Leveraging Social Influence based on Users Activity Centers for Point-of-Interest Recommendation

Serve TensorFlow ML models with TF-Serving and then create a Streamlit UI to use them

ZSL-KG is a general-purpose zero-shot learning framework with a novel transformer graph convolutional network (TrGCN) to learn class representation from common sense knowledge graphs.

Python package for visualizing the loss landscape of parameterized quantum algorithms.

We present a regularized self-labeling approach to improve the generalization and robustness properties of fine-tuning.

Style transfer, deep learning, feature transform

Exploring Versatile Prior for Human Motion via Motion Frequency Guidance (3DV2021)

A Tensorflow implementation of CapsNet based on Geoffrey Hinton's paper Dynamic Routing Between Capsules

An experimentation and research platform to investigate the interaction of automated agents in an abstract simulated network environments.

Code for the Active Speakers in Context Paper (CVPR2020)

Using deep actor-critic model to learn best strategies in pair trading