Research map / Detection and segmentation / Open-set and few-shot detection
Joint Gap Detection and Inpainting of Line Drawings
Kazuma Sasaki, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa
Check 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 |
|---|---|---|---|
| automatically detect gaps and complete line drawings without an input mask | CNN line-drawing completion · User study, 20 images | preference over PatchMatch: 93.9% | Improved |
| automatically detect gaps and complete line drawings without an input mask | CNN line-drawing completion · User study, 20 images | preference over Image Melding: 95.8% | Improved |
| use an input mask (ablation) | CNN line-drawing completion · User study, 20 images | preference between masked and unmasked Ours: 53.9% | No clear effect |
| use an input mask (ablation) | CNN line-drawing completion · Mean across scanned and synthetic data | rating (scale 1 to 5): 4.2 -> 4.2 | No clear effect |
| reduce filter counts in later network layers (ablation) | CNN line-drawing completion · line-drawing completion | performance | No clear effect |
| reduce filter counts in later network layers (ablation) | CNN line-drawing completion · line-drawing completion | memory usage: roughly 30% | Improved |
| reduce filter counts in later network layers (ablation) | CNN line-drawing completion · line-drawing completion | computation time: nearly half | Improved |
Closest papers by meaning
- Neural Contours: Learning to Draw Lines From 3D Shapes (CVPR 2020 · similarity 0.86)
- Contextual-based Image Inpainting: Infer, Match, and Translate (ECCV 2018 · similarity 0.85)
- Learning To Generate Line Drawings That Convey Geometry and Semantics (CVPR 2022 · similarity 0.85)
- Constrained Convolutional Sparse Coding for Parametric Based Reconstruction of Line Drawings (ICCV 2017 · similarity 0.85)
- Foreground-Aware Image Inpainting (CVPR 2019 · similarity 0.84)
- Scene Categorization From Contours: Medial Axis Based Salience Measures (CVPR 2019 · 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.
