Research map / Image generation / Editing and style transfer
Scraping Textures from Natural Images for Synthesis and Editing
Xueting Li, Xiaolong Wang, Ming-Hsuan Yang, Alexei A. Efros, Sifei Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add learned image grouping instead of using SLIC superpixels as texture segments (ablation) | Texture synthesis model · Texture synthesis (qualitative) | visual quality of synthesized texture | Improved |
| add parametric sine wave input instead of noise to the decoder (ablation) | Texture synthesis model · Texture synthesis (qualitative) | visual quality on stationary patterns | Improved |
| our method vs Image Quilting, the strongest baseline, on patch FID | Texture synthesis · Texture synthesis (104 ImageNet images) | c-FID: 76.80 -> 72.36 | Improved |
| our method vs Image Quilting on masked patch LPIPS | Texture synthesis · Texture synthesis (104 ImageNet images) | c-LPIPS (mask): 0.3568 -> 0.3193 | Improved |
| our method vs Normalized Cuts on boundary recall | Image grouping · BSDS500 test | Boundary Recall: 0.3 -> 0.67 | Improved |
| our method vs Normalized Cuts on boundary precision | Image grouping · BSDS500 test | Boundary Precision: 0.38 -> 0.27 | Hurt |
| our unsupervised grouping vs supervised SuperpixelFCN on ASA | Image grouping · BSDS500 test | ASA: 0.83 -> 0.68 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PSGAN — PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer (CVPR 2020) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture (CVPR 2019 · similarity 0.87)
- Diversified Texture Synthesis With Feed-Forward Networks (CVPR 2017 · similarity 0.86)
- Toward a Universal Model for Shape From Texture (CVPR 2020 · similarity 0.86)
- Generating Non-Stationary Textures using Self-Rectification (CVPR 2024 · similarity 0.85)
- TextureDreamer: Image-Guided Texture Synthesis Through Geometry-Aware Diffusion (CVPR 2024 · similarity 0.85)
- TexTile: A Differentiable Metric for Texture Tileability (CVPR 2024 · similarity 0.84)
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.
