Research map / Image generation / Editing and style transfer
Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Texture Mixer instead of Image Melding | Texture interpolation · Earth and animal texture (average) | Preference rate: 0.672 | Mixed |
| Use Texture Mixer instead of PSGAN | Texture interpolation · Earth and animal texture (average) | Preference rate: 0.967 | Helped |
| Use Texture Mixer instead of Image Melding | Texture interpolation · Earth and animal texture (average) | Testing time: 6 min -> 0.5 s | Helped |
| Add a global latent z^g (ablation) | Texture Mixer · Earth and animal texture (average) | CCD: 0.680 -> 0.623 | Helped |
| Add texture blending during training (ablation) | Texture Mixer · Earth and animal texture (average) | CSWD: 52.29 -> 22.10 | Helped |
| Add latent-space random shuffling (ablation) | Texture Mixer · Earth and animal texture (average) | CRS: 0.2386 -> 0.0008 | Helped |
| Remove latent-space random shuffling (ablation) | Texture Mixer · Earth and animal texture (average) | CIS: 26.68 -> 26.78 | No clear effect |
| Remove latent-space random shuffling (ablation) | Texture Mixer · Earth and animal texture (average) | CCD: 0.623 -> 0.490 | Helped |
| Remove latent-space random shuffling (ablation) | Texture Mixer · Earth and animal texture (average) | CSS: 0.0066 -> 0.0534 | Hurt |
Closest papers by meaning
- Diversified Texture Synthesis With Feed-Forward Networks (CVPR 2017 · similarity 0.90)
- Texture Networks: Feed-forward Synthesis of Textures and Stylized Images (ICML 2016 · similarity 0.89)
- TextureDreamer: Image-Guided Texture Synthesis Through Geometry-Aware Diffusion (CVPR 2024 · similarity 0.87)
- Generating Non-Stationary Textures using Self-Rectification (CVPR 2024 · similarity 0.86)
- Single Mesh Diffusion Models with Field Latents for Texture Generation (CVPR 2024 · similarity 0.86)
- Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.