# Texture Synthesis with Recurrent Variational Auto-Encoder

arXiv: https://arxiv.org/abs/1712.08838 · HTML: https://mlsanity.com/paper/1712.08838/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2017.

## Built on by (most cited first, 1 of 1)

- [Texture Image Synthesis Using Spatial GAN Based on Vision Transformers](https://mlsanity.com/paper/2502.01842/) (2025)

## Abstract (arXiv)

We propose a recurrent variational auto-encoder for texture synthesis. A novel loss function, FLTBNK, is used for training the texture synthesizer. It is rotational and partially color invariant loss function. Unlike L2 loss, FLTBNK explicitly models the correlation of color intensity between pixels. Our texture synthesizer generates neighboring tiles to expand a sample texture and is evaluated using various texture patterns from Describable Textures Dataset (DTD). We perform both quantitative and qualitative experiments with various loss functions to evaluate the performance of our proposed loss function (FLTBNK) --- a mini-human subject study is used for the qualitative evaluation.