User-Controllable Multi-Texture Synthesis with Generative Adversarial Networks

Alanov, Aibek; Kochurov, Max; Volkhonskiy, Denis; Yashkov, Daniil; Burnaev, Evgeny; Vetrov, Dmitry

doi:10.48550/arxiv.1904.04751

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A more recent line of work [Alanov et al 2019;Bergmann et al 2017;Frühstück et al 2019;Jetchev et al 2016;Li and Wand 2016;Li et al 2017b;Shaham et al 2019;Zhou et al 2018] has proposed using Generative Adversarial Networks (GANs) for more realistic texture synthesis while still suffering from the inability to generalize to new unseen textures. Zhou et al [Zhou et al 2018] learn a generator network that expands k × k texture blocks into 2k × 2k output through a combination of adversarial, L 1 , and style (gram matrix) loss.…”

Section: Related Workmentioning

confidence: 99%

“…Other efforts [Alanov et al 2019;Bergmann et al 2017;Frühstück et al 2019;Jetchev et al 2016;Li et al 2017b] try to train on a set of texture images. During test time, the texture being generated is either chosen by the network [Bergmann et al 2017;Jetchev et al 2016] or user-controlled [Alanov et al 2019;Li et al 2017b]. [Frühstück et al 2019] propose a non-parametric method to synthesize large-scale, varied outputs by combining intermediate feature maps.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter

Liu¹,

Taori²,

Wang³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter

Liu¹,

Taori²,

Wang³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Most such approaches learn purely generative models, often trained on individual exemplars. An effective technique to incorporate a user-provided exemplar is conditional GANs [20], as shown by Alanov et al [21]. Here, G synthesizes a texture given an exemplar patch as input.…”

Section: Related Workmentioning

confidence: 99%

GramGAN: Deep 3D Texture Synthesis From 2D Exemplars

Portenier,

Bigdeli,

Goksel

2020

Preprint

View full text Add to dashboard Cite

We present a novel texture synthesis framework, enabling the generation of infinite, high-quality 3D textures given a 2D exemplar image. Inspired by recent advances in natural texture synthesis, we train deep neural models to generate textures by non-linearly combining learned noise frequencies. To achieve a highly realistic output conditioned on an exemplar patch, we propose a novel loss function that combines ideas from both style transfer and generative adversarial networks. In particular, we train the synthesis network to match the Gram matrices of deep features from a discriminator network. In addition, we propose two architectural concepts and an extrapolation strategy that significantly improve generalization performance. In particular, we inject both model input and condition into hidden network layers by learning to scale and bias hidden activations. Quantitative and qualitative evaluations on a diverse set of exemplars motivate our design decisions and show that our system performs superior to previous state of the art. Finally, we conduct a user study that confirms the benefits of our framework.Preprint. Under review.

show abstract

User-Controllable Multi-Texture Synthesis with Generative Adversarial Networks

Cited by 2 publications

References 0 publications

Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter

Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter

GramGAN: Deep 3D Texture Synthesis From 2D Exemplars

Contact Info

Product

Resources

About