Research map / 3D vision / Face and shape
Learning Cross-Domain Neural Networks for Sketch-Based 3D Shape Retrieval
Read the paperCheck 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 |
|---|---|---|---|
| add cross-domain neural network transfer (identical class targets) vs none (ablation) | low-level features · SHREC'14 complete benchmark | NN: 0.007 -> 0.954 | Helped |
| add pyramid structure (PCDNN vs CDNN) (ablation) | CDNN · SHREC'14 complete benchmark | NN: 0.954 -> 1.457 | Helped |
| add pyramid structure (PCDNN vs CDNN) (ablation) | CDNN · SHREC'14 testing dataset | NN: 2.515 -> 5.175 | Helped |
| add pyramid structure (PCDNN vs CDNN) (ablation) | CDNN · SHREC'14 complete benchmark | FT: 0.600 -> 0.911 | Helped |
| add pyramid structure (PCDNN vs CDNN) (ablation) | CDNN · SHREC'14 complete benchmark | DCG: 3.706 -> 3.375 | Mixed |
| PCDNN vs SCMR-OPHOG at higher recall (ablation) | PCDNN · SHREC'14 PR curve | precision at recall > 0.4 | Hurt |
| CDNN vs SCMR-OPHOG baseline (ablation) | CDNN · SHREC'14 complete benchmark | NN: 0.345 -> 0.954 | Helped |
Closest papers by meaning
- Deep Correlated Metric Learning for Sketch-based 3D Shape Retrieval (AAAI 2017 · similarity 0.89)
- Learning Barycentric Representations of 3D Shapes for Sketch-Based 3D Shape Retrieval (CVPR 2017 · similarity 0.89)
- Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval (AAAI 2022 · similarity 0.88)
- Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing (CVPR 2019 · similarity 0.87)
- Doodle to Object: Practical Zero-Shot Sketch-Based 3D Shape Retrieval (AAAI 2023 · similarity 0.87)
- SketchINR: A First Look into Sketches as Implicit Neural Representations (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.