Research map / Label-efficient and robust learning / Self-supervised and contrastive
PhySpec: Physically Consistent Spectral Reconstruction via Orthogonal Subspace Decomposition and Self-Supervised Meta-Auxiliary Learning
Xingxing Yang, Jie Chen, Zaifeng Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes PhySpec, a spectral reconstruction method from RGB that targets colorimetric consistency (predicted HSI should reproduce ground-truth RGB) using orthogonal subspace decomposition and self-supervised meta-auxiliary learning.
Problem
Learning-based hyperspectral image reconstruction from RGB often fails to consistently reproduce the ground-truth RGB from the predicted HSI, the so-called "colorimetric dilemma", compromising physical integrity.
Approach
Combines an orthogonal subspace decomposition of the spectral output with self-supervised meta-auxiliary learning to enforce physically consistent reconstructions that reproduce the input RGB; details beyond the abstract are not available.
Closest papers by meaning
- Unraveling Metameric Dilemma for Spectral Reconstruction: A High-Fidelity Approach via Semi-Supervised Learning (NeurIPS 2025 · similarity 0.91)
- Semantic-Embedded Unsupervised Spectral Reconstruction From Single RGB Images in the Wild (ICCV 2021 · similarity 0.90)
- EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution (AAAI 2025 · similarity 0.89)
- Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery (ECCV 2018 · similarity 0.89)
- FRN: Fractal-Based Recursive Spectral Reconstruction Network (NeurIPS 2025 · similarity 0.88)
- Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification (CVPR 2024 · similarity 0.87)
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.
