Image Shape Manipulation from a Single Augmented Training Sample (2020-07-02T00:00:00.000000Z)

TL;DR

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.

Abstract

In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of thin-plate-spline (TPS) as an effective augmentation. Our network learns to map between a primitive representation of the image to the image itself. The choice of a primitive representation has an impact on the ease and expressiveness of the manipulations and can be automatic (e.g. edges), manual (e.g. segmentation) or hybrid such as edges on top of segmentations. At manipulation time, our generator allows for making complex image changes by modifying the primitive input representation and mapping it through the network. Our method is shown to achieve remarkable performance on image manipulation tasks.

Authors

Eliahu Horwitz

3 papers

Yael Vinker

3 papers

Nir Zabari

1 papers

TL;DR

Abstract

Authors

References46 items

Reference-Based Sketch Image Colorization Using Augmented-Self Reference and Dense Semantic Correspondence

Interactive video stylization using few-shot patch-based training

TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images

Few-shot Video-to-Video Synthesis

An Augmentation Strategy for Medical Image Processing Based on Statistical Shape Model and 3D Thin Plate Spline for Deep Learning

CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features

SinGAN: Learning a Generative Model From a Single Natural Image

A critical analysis of self-supervision, or what we can learn from a single image

Adversarial Learning of General Transformations for Data Augmentation

Semantic Image Synthesis With Spatially-Adaptive Normalization

Data Augmentation Using Learned Transformations for One-Shot Medical Image Segmentation

Internal Distribution Matching for Natural Image Retargeting

Video-to-Video Synthesis

AutoAugment: Learning Augmentation Policies from Data

Non-stationary texture synthesis by adversarial expansion

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric

SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis

Smart, Sparse Contours to Represent and Edit Images

Zero-Shot Super-Resolution Using Deep Internal Learning

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

Deep Image Prior

StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation

VITON: An Image-Based Virtual Try-on Network

Toward Multimodal Image-to-Image Translation

Learning Texture Manifolds with the Periodic Spatial GAN

Learning to Discover Cross-Domain Relations with Generative Adversarial Networks

Unsupervised Image-to-Image Translation Networks

Texture Synthesis with Spatial Generative Adversarial Networks

Image-to-Image Translation with Conditional Adversarial Networks

Generative Visual Manipulation on the Natural Image Manifold

WarpNet: Weakly Supervised Matching for Single-View Reconstruction

Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks

The Cityscapes Dataset for Semantic Urban Scene Understanding

Perceptual Losses for Real-Time Style Transfer and Super-Resolution

Shift-map image editing

PatchMatch: a randomized correspondence algorithm for structural image editing

Seam Carving for Content-Aware Image Resizing

Poisson image editing

Approximate Thin Plate Spline Mappings

Image Analogies

Image Warping by Radial Basis Functions: Application to Facial Expressions

Feature-based image metamorphosis

A Computational Approach to Edge Detection

Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

GENERATIVE ADVERSARIAL NETS

Computer Vision - Algorithms and Applications

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names