A geometrically aware auto-encoder for multi-texture synthesis
This addresses texture synthesis for computer graphics and vision applications, but appears incremental as it builds on existing auto-encoder methods with specific enhancements.
The paper tackled the problem of multi-texture synthesis by proposing an auto-encoder architecture that embeds images in a geometrically consistent latent space, outperforming state-of-the-art feed-forward methods in visual quality and texture metrics.
We propose an auto-encoder architecture for multi-texture synthesis. The approach relies on both a compact encoder accounting for second order neural statistics and a generator incorporating adaptive periodic content. Images are embedded in a compact and geometrically consistent latent space, where the texture representation and its spatial organisation are disentangled. Texture synthesis and interpolation tasks can be performed directly from these latent codes. Our experiments demonstrate that our model outperforms state-of-the-art feed-forward methods in terms of visual quality and various texture related metrics.