Non-stationary texture synthesis by adversarial expansion
Explore this paper's citation graph
Summary
This paper proposes a new approach for example-based non-stationary texture synthesis that uses a generative adversarial network (GAN), trained to double the spatial extent of texture blocks extracted from a specific texture exemplar, and demonstrates that it can cope with challenging textures, which no other existing method can handle.
- Type
- article
- Published
- 2018-05-11
- Cited by
- 229
- References
- 31
- Access
- Open access
- OpenAlex
- https://openalex.org/W2801495938
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:21661885
Keywords
Texture synthesis, Computer science, Texture (cosmology), Generator (circuit theory), Artificial intelligence
References
- State of the Art in Example-based Texture Synthesis
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- A Neural Algorithm of Artistic Style
- Self Tuning Texture Optimization
- Texture optimization for example-based synthesis
- Image melding
- Appearance-space texture synthesis
- Image quilting for texture synthesis and transfer
- Synthesis of progressively-variant textures on arbitrary surfaces
- Graphcut textures: image and video synthesis using graph cuts
- Generative Adversarial Nets
- Texture synthesis by non-parametric sampling
- Near-regular texture analysis and manipulation
- Texture Synthesis Using Convolutional Neural Networks
- Space-Time Completion of Video
- Layered shape synthesis: automatic generation of control maps for non-stationary textures
- Deep Residual Learning for Image Recognition
- Fast texture synthesis using tree-structured vector quantization
- Image Analogies
- Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
Cited by
- Texture synthesis guided deep hashing for texture image retrieval
- Dynamic-Net: Tuning the Objective Without Re-Training for Synthesis Tasks
- Internal Distribution Matching for Natural Image Retargeting
- On Demand Solid Texture Synthesis Using Deep 3D Networks
- Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
- Learning GAN fingerprints towards Image Attribution
- User-Controllable Multi-Texture Synthesis with Generative Adversarial Networks
- TileGAN
- SinGAN: Learning a Generative Model From a Single Natural Image
- Planar Abstraction and Inverse Rendering of 3D Indoor Environments
- Automatic extraction and synthesis of regular repeatable patterns
- InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations
- Facial Image Inpainting Using Multi-level Generative Network
- Point Pattern Synthesis via Irregular Convolution
- Program-Guided Image Manipulators
- GAN-Leaks: A Taxonomy of Membership Inference Attacks against GANs
- Texture Synthesis in a Weighted Graph Using Nth-Order Voronoi Diagrams
- Interactive Curation of Datasets for Training and Refining Generative Models
- A novel framework for inverse procedural texture modeling
- Orometry-based terrain analysis and synthesis
Related papers
- Sample-Based Texture Synthesis
- Asymptotically Admissible Texture Synthesis
- The Research of Texture Transmission Algorithm Combined with Texture Synthesis
- Is there any texture in the image?
- Texturing and line art rendering using patch-based image analogies
- Image texture synthesis method based on the trend function constraint
- Texture Transfer in Frequency Domain
- Steganography Using Reversible Texture Synthesis