SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches

Last update: Dec 25, 2022

Related tags

Deep Learning sketchedit

Overview

SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches

[Paper] [Project Page] [Interactive Demo] [Supplementary Material]

Usage

environment

The code only has been tested on Ubuntu 20.04.

GPU is required.

Clone the repo:

git clone --single-branch https://github.com/zengxianyu/sketchedit
git submodule init
git submodule update

Install using the provided docker file Dockerfile or

conda env create -f environment.yml

Switch to the installed environment

conda activate editline

Testing

Download pretrained model

chmod +x download/*
./download/download_model.sh

Use the model trained on CelebAHQ

./test_celeb.sh

Use the model trained on Places

./test_places.sh

Interactive demo

http://47.57.135.203:8001/

Training code and data

Training code and data will be released after the paper is published.

Acknowledgments

DeepFill https://github.com/jiahuiyu/generative_inpainting
Pix2PixHD https://github.com/NVIDIA/pix2pixHD
SPADE https://github.com/NVlabs/SPADE

SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches

Related tags

Overview

SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches

Usage

environment

Testing

Interactive demo

Training code and data

Acknowledgments

Owner

Back to Basics: Efficient Network Compression via IMP

Distance Encoding for GNN Design

A graphical Semi-automatic annotation tool based on labelImg and Yolov5

SingleVC performs any-to-one VC, which is an important component of MediumVC project.

Augmented CLIP - Training simple models to predict CLIP image embeddings from text embeddings, and vice versa.

Source code for Fixed-Point GAN for Cloud Detection

TensorFlow implementation of "A Simple Baseline for Bayesian Uncertainty in Deep Learning"

Lunar is a neural network aimbot that uses real-time object detection accelerated with CUDA on Nvidia GPUs.

Christmas face app for Decathlon xmas coding party!

GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation. (CVPR 2021)

Post-training Quantization for Neural Networks with Provable Guarantees

NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework

Solving reinforcement learning tasks which require language and vision

Attack classification models with transferability, black-box attack; unrestricted adversarial attacks on imagenet

Demonstrates how to divide a DL model into multiple IR model files (division) and introduce a simplest way to implement a custom layer works with OpenVINO IR models.

ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs

ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives

3D AffordanceNet is a 3D point cloud benchmark consisting of 23k shapes from 23 semantic object categories, annotated with 56k affordance annotations and covering 18 visual affordance categories.

PyTorch Implementation of Spatially Consistent Representation Learning(SCRL)

Tensorflow Implementation of SMU: SMOOTH ACTIVATION FUNCTION FOR DEEP NETWORKS USING SMOOTHING MAXIMUM TECHNIQUE