Research map / Image generation / Editing and style transfer
r-BTN: Cross-Domain Face Composite and Synthesis From Limited Facial Patches
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 |
|---|---|---|---|
| Use bidirectional face–sketch transformations instead of independently trained one-way mappings | r-BTN · Face/sketch generation from limited patches | identity and domain consistency | Helped |
| Add the given-patch constraint during recursive generation (ablation) | r-BTN · Face/sketch generation from limited patches | preservation of input-patch identity | Helped |
| Add the adversarial constraint during recursive generation (ablation) | r-BTN · Face/sketch generation from limited patches | realism | Helped |
| Use both the given-patch and adversarial constraints during recursive generation (ablation) | r-BTN · Face/sketch generation from limited patches | overall visual quality | Helped |
| Increase the missing proportion beyond 70% | r-BTN · Face synthesis from limited facial patches | identity preservation | Hurt |
| Use eye patches rather than nose or mouth patches | r-BTN · Face synthesis from patches of the same person | generated-face similarity | Helped |
Closest papers by meaning
- InverseFaceNet: Deep Monocular Inverse Face Rendering (CVPR 2018 · similarity 0.88)
- Unsupervised Cross-Domain Image Generation (ICLR 2017 · similarity 0.86)
- R3 Adversarial Network for Cross Model Face Recognition (CVPR 2019 · similarity 0.86)
- Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation (CVPR 2024 · similarity 0.86)
- OSDFace: One-Step Diffusion Model for Face Restoration (CVPR 2025 · similarity 0.85)
- CapHuman: Capture Your Moments in Parallel Universes (CVPR 2024 · similarity 0.85)
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.