Saved in:
Bibliographic Details
Main Authors: Yin, Liping, Chua, Albert
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2211.11137
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917586448416768
author Yin, Liping
Chua, Albert
author_facet Yin, Liping
Chua, Albert
contents 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 or user-added spatial tags to capture long range constraints in images. Having access to a user-added spatial tag for all situations is not always feasible, and regularization terms can be difficult to tune. Thus, we propose a new set of statistics for texture synthesis based on Sliced Wasserstein Loss, create a multi-scale method to synthesize textures without a user-added spatial tag, study the ability of our proposed method to capture long range constraints, and compare our results to other optimization-based, single texture synthesis algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2211_11137
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Long Range Constraints for Neural Texture Synthesis Using Sliced Wasserstein Loss
Yin, Liping
Chua, Albert
Computer Vision and Pattern Recognition
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 or user-added spatial tags to capture long range constraints in images. Having access to a user-added spatial tag for all situations is not always feasible, and regularization terms can be difficult to tune. Thus, we propose a new set of statistics for texture synthesis based on Sliced Wasserstein Loss, create a multi-scale method to synthesize textures without a user-added spatial tag, study the ability of our proposed method to capture long range constraints, and compare our results to other optimization-based, single texture synthesis algorithms.
title Long Range Constraints for Neural Texture Synthesis Using Sliced Wasserstein Loss
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2211.11137