# Long Range Constraints for Neural Texture Synthesis Using Sliced Wasserstein Loss

arXiv: https://arxiv.org/abs/2211.11137 · HTML: https://mlsanity.com/paper/2211.11137/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 21 Nov 2022.

## Builds on (most cited first, 12 of 12)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesis](https://mlsanity.com/paper/1701.02096/) (2017)
- [Effectively Unbiased FID and Inception Score and where to find them](https://mlsanity.com/paper/1911.07023/) (2019)
- [Non-Stationary Texture Synthesis by Adversarial Expansion](https://mlsanity.com/paper/1805.04487/) (2018)
- [Texture Synthesis Through Convolutional Neural Networks and Spectrum Constraints](https://mlsanity.com/paper/1605.01141/) (2016)
- [Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter](https://mlsanity.com/paper/2007.07243/) (2020)
- [High resolution neural texture synthesis with long range constraints](https://mlsanity.com/paper/2008.01808/) (2020)
- [Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction](https://mlsanity.com/paper/2104.12939/) (2021)
- [Generalized Rectifier Wavelet Covariance Models For Texture Synthesis](https://mlsanity.com/paper/2203.07902/) (2022)

## Abstract (arXiv)

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.