Texture synthesis via projection onto multiscale, multilayer statistics
Not on the map. Why?
Abstract (arXiv)
We provide a new model for texture synthesis based on a multiscale, multilayer feature extractor. Within the model, textures are represented by a set of statistics computed from ReLU wavelet coefficients at different layers, scales and orientations. A new image is synthesized by matching the target statistics via an iterative projection algorithm. We explain the necessity of the different types of pre-defined wavelet filters used in our model and the advantages of multilayer structures for image synthesis. We demonstrate the power of our model by generating samples of high quality textures and providing insights into deep representations for texture images.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 11 of its 24 references that are in the map. First posted on arXiv 22 May 2021.
Builds on
11 of 24 references.
References · 11
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
- 2015A Neural Algorithm of Artistic Stylecited by 483
- 2016Texture Networks: Feed-forward Synthesis of Textures and Stylized Imagescited by 174
- 2017Learning Texture Manifolds with the Periodic Spatial GANcited by 53
- 2017TextureGAN: Controlling Deep Image Synthesis with Texture Patchescited by 47
- 2016Texture Synthesis with Spatial Generative Adversarial Networkscited by 45
- 2018Exposition and Interpretation of the Topology of Neural Networkscited by 20
- 2018Multiscale Sparse Microcanonical Modelscited by 14
- 2019Maximum Entropy Models from Phase Harmonic Covariancescited by 13
- 2019Macrocanonical Models for Texture Synthesiscited by 1
Built on by
Citing papers per year: 2022: 1.
1 paper.