Long Range Constraints for Neural Texture Synthesis Using Sliced Wasserstein Loss

11/21/2022
by   Liping Yin, et al.
0

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. It would be ideal to create an algorithm that does not have any of the aforementioned drawbacks. Thus, we propose a new set of statistics for exemplar based texture synthesis based on Sliced Wasserstein Loss and create a multi-scale algorithm to synthesize textures without a user-added spatial tag. Lastly, we study the ability of our proposed algorithm to capture long range constraints in images and compare our results to other exemplar-based neural texture synthesis algorithms.

READ FULL TEXT

page 3

page 4

research
08/04/2020

High resolution neural texture synthesis with long range constraints

The field of texture synthesis has witnessed important progresses over t...
research
04/13/2021

Dynamic Texture Synthesis by Incorporating Long-range Spatial and Temporal Correlations

The main challenge of dynamic texture synthesis lies in how to maintain ...
research
10/07/2022

Pose Guided Human Image Synthesis with Partially Decoupled GAN

Pose Guided Human Image Synthesis (PGHIS) is a challenging task of trans...
research
06/03/2016

Incorporating long-range consistency in CNN-based texture generation

Gatys et al. (2015) showed that pair-wise products of features in a conv...
research
07/29/2018

Texture Mixing by Interpolating Deep Statistics via Gaussian Models

Recently, enthusiastic studies have devoted to texture synthesis using d...
research
02/23/2022

Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesis

We present a novel U-Attention vision Transformer for universal texture ...
research
06/12/2020

Pitfalls of the Gram Loss for Neural Texture Synthesis in Light of Deep Feature Histograms

Neural texture synthesis and style transfer are both powered by the Gram...

Please sign up or login with your details

Forgot password? Click here to reset