A Sliced Wasserstein Loss for Neural Texture Synthesis
We address the problem of computing a textural loss based on the statistics extracted from the feature activations of a convolutional neural network optimized for object recognition (e.g. VGG-19). The underlying mathematical problem is the measure of the distance between two distributions in feature space. The Gram-matrix loss is the ubiquitous approximation for this problem but it is subject to several shortcomings. Our goal is to promote the Sliced Wasserstein Distance as a replacement for it. It is theoretically proven,practical, simple to implement, and achieves results that are visually superior for texture synthesis by optimization or training generative neural networks.
Code (3)
Similar Papers 제목 키워드 기반
Long Range Constraints for Neural Texture Synthesis Using Sliced Wasserstein Loss
In the past decade, exemplar-based texture synthesis algorithms have seen strong gains in performance by matching statistics of deep convolutional neural networks. However, these algorithms require regularization terms o…
TAGTexture SynthesisNeural Texture Synthesis With Guided Correspondence
Markov random fields (MRFs) are the cornerstone of classical approaches to example-based texture synthesis. Yet, it is not fully valued in the deep learning era. This paper aims to re-promote the combination of MRFs …
Texture SynthesisAmortized Projection Optimization for Sliced Wasserstein Generative Models
Seeking informative projecting directions has been an important task in utilizing sliced Wasserstein distance in applications. However, finding these directions usually requires an iterative optimization procedure over t…
Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model
In this paper we study generative modeling via autoencoders while using the elegant geometric properties of the optimal transport (OT) problem and the Wasserstein distances. We introduce Sliced-Wasserstein Autoencoders (…
modelSliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model
In this paper we study generative modeling via autoencoders while using the elegant geometric properties of the optimal transport (OT) problem and the Wasserstein distances. We introduce Sliced-Wasserstein Autoencoders (…
model