Research map / 3D vision / Depth and stereo
Hyper-Skin: A Hyperspectral Dataset for Reconstructing Facial Skin-Spectra from RGB Images
Pai Chet Ng, Zhixiang Chi, Yannick Verdie, Juwei Lu, Konstantinos N Plataniotis
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 |
|---|---|---|---|
| re-train on Hyper-Skin instead of NTIRE2022 pre-trained weights | HSCNN · Hyper-Skin (RGB, VIS) with background | SSIM: 0.683 ± 0.027 -> 0.916 ± 0.013 | Improved |
| re-train on Hyper-Skin instead of NTIRE2022 pre-trained weights | MST++ · Hyper-Skin (RGB, VIS) with background | SSIM: 0.602 ± 0.042 -> 0.923 ± 0.011 | Improved |
| re-train on Hyper-Skin instead of NTIRE2022 pre-trained weights | HRNet · Hyper-Skin (RGB, VIS) with background | SAM: 0.648 ± 0.062 -> 0.147 ± 0.014 | Improved |
| re-train on Hyper-Skin instead of NTIRE2022 pre-trained weights | MST++ · Hyper-Skin (RGB, VIS) w/o background | SAM: 0.628 ± 0.050 -> 0.107 ± 0.010 | Improved |
| remove background with a mask when evaluating (ablation) | MST++ pre-trained · Hyper-Skin (RGB, VIS) | SSIM: 0.602 ± 0.042 -> 0.766 ± 0.035 | Improved |
| remove background with a mask when evaluating (ablation) | HSCNN re-trained · Hyper-Skin (RGB, VIS) | SSIM: 0.916 ± 0.013 -> 0.950 ± 0.011 | Improved |
| remove background with a mask when evaluating (ablation) | HRNet re-trained · Hyper-Skin (MSI, NIR) | SAM: 0.094 ± 0.009 -> 0.086 ± 0.010 | Improved |
| use (MSI, NIR) 4-channel input instead of (RGB, VIS) | MST++ re-trained · Hyper-Skin with background | SAM: 0.113 ± 0.009 -> 0.086 ± 0.006 | Improved |
| use (MSI, NIR) 4-channel input instead of (RGB, VIS) | HRNet re-trained · Hyper-Skin with background | SSIM: 0.933 ± 0.021 -> 0.955 ± 0.006 | Improved |
Closest papers by meaning
- HUST: High-Fidelity Unbiased Skin Tone Estimation via Texture Quantization (ICCV 2025 · similarity 0.87)
- S^3-Face: SSS-Compliant Facial Reflectance Estimation via Diffusion Priors (CVPR 2025 · similarity 0.86)
- Monocular Identity-Conditioned Facial Reflectance Reconstruction (CVPR 2024 · similarity 0.84)
- SFDM: Robust Decomposition of Geometry and Reflectance for Realistic Face Rendering from Sparse-view Images (CVPR 2025 · similarity 0.82)
- FRN: Fractal-Based Recursive Spectral Reconstruction Network (NeurIPS 2025 · similarity 0.82)
- Hypergraph-Guided Disentangled Spectrum Transformer Networks for Near-Infrared Facial Expression Recognition (AAAI 2024 · similarity 0.82)
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.
