computer-vision-4

Sketch-to-Image Translation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in sketch-to-image-translation-4

Trend

Dataset

Best Model

Actions

COCO-Stuff

SketchyCOCO

Scribble

Libraries

i

Use these libraries to find sketch-to-image-translation-4 models and implementations

Datasets

Subtasks

No subtasks available.

Most implemented papers

Semantic Image Synthesis With Spatially-Adaptive Normalization

Ming-Yu Liu, Jun-Yan Zhu, Ting-Chun Wang, Taesung Park•Sun Mar 17 2019

S spatially-adaptive normalization is proposed, a simple but effective layer for synthesizing photorealistic images given an input semantic layout that allows users to easily control the style and content of image synthesis results as well as create multi-modal results.

3008

Content

0

Paper Graph

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

Bryan Catanzaro, Ming-Yu Liu, Jan Kautz, Jun-Yan Zhu, Ting-Chun Wang, Andrew Tao•Wed Nov 29 2017

A new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs) is presented, which significantly outperforms existing methods, advancing both the quality and the resolution of deep image synthesis and editing.

4278 0

Paper Graph

SketchyCOCO: Image Generation From Freehand Scene Sketches

Limin Wang, Jianzhuang Liu, C. Zou, Chengying Gao, Qi Liu, Qi Xu•Wed Mar 04 2020

This work introduces the first method for automatic image generation from scene-level freehand sketches that allows for controllable image generation by specifying the synthesis goal via free hand sketches and builds a large-scale composite dataset called SketchyCOCO to support and evaluate the solution.

137 0

Paper Graph

Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis

Ding Liu, Xiaohui Shen, Xiaoyu Xiang, J. Allebach, Xiao Yang•Sun Apr 11 2021

This paper proposes a simple yet effective open-domain sampling and optimization strategy to "fool" the generator into treating fake sketches as real ones, and shows impressive results in synthesizing realistic color, texture, and maintaining the geometric composition for various categories of open- domain sketches.

47 0

Paper Graph

Pretraining is All You Need for Image-to-Image Translation

Ting Zhang, Dong Chen, Hao Ouyang, Tengfei Wang, Fang Wen, Bo Zhang, Qifeng Chen•Tue May 24 2022

Examination of the proposed pretraining-based image-to-image translation (PITI) is shown to be capable of synthesizing images of unprecedented realism and faithfulness, and an adversarial training to enhance the texture synthesis in the diffusion model training is proposed.

200 0

Paper Graph

MaskSketch: Unpaired Structure-guided Masked Image Generation

Kihyuk Sohn, Kate Saenko, D. Bashkirova, José Lezama, Irfan Essa•Thu Feb 09 2023

The paper shows that intermediate self-attention maps of a masked generative transformer encode important structural information of the input image, such as scene layout and object shape, and proposes a novel sampling method based on this observation to enable structure-guided generation in MaskSketch.

38 0

Paper Graph

Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation

Richard Zhang, Alexei A. Efros, Eli Shechtman, Oliver Wang, Philip H. S. Torr, Arna Ghosh, P. Dokania•Mon Sep 23 2019

An interactive GAN-based sketch-to-image translation method that helps novice users easily create images of simple objects and introduces a gating-based approach for class conditioning, which allows for distinct classes without feature mixing, from a single generator network.

142 0

Paper Graph

Image Shape Manipulation from a Single Augmented Training Sample

Eliahu Horwitz, Yael Vinker, Nir Zabari, Yedid Hoshen•Wed Jul 01 2020

DeepSIM, a generative model for conditional image manipulation based on a single image, finds that extensive augmentation is key for enabling single image training, and incorporates the use of thin-plate-spline (TPS) as an effective augmentation.

22 0

Paper Graph

Adding a benchmark result helps the community track progress.