Research map / Image generation / Image restoration
Spectral Compressive Imaging via Unmixing-driven Subspace Diffusion Refinement
Haijin Zeng, Benteng Sun, Yongyong Chen, Jingyong Su, Yong Xu
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 an unmixing-driven subspace diffusion refinement approach for spectral compressive imaging reconstruction to recover high-frequency details.
Problem
Spectral Compressive Imaging (SCI) reconstruction is ill-posed since a single observation admits multiple plausible reconstructions; deterministic methods struggle to recover high-frequency details, and diffusion models are limited by scarce training data and high computational cost.
Approach
Applies diffusion refinement within a subspace derived from spectral unmixing, rather than over full hyperspectral images, to reduce computational demands and cope with limited training data.
Closest papers by meaning
- Self-Supervised One-Step Diffusion Refinement for Snapshot Compressive Imaging (AAAI 2026 · similarity 0.92)
- DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model (CVPR 2024 · similarity 0.91)
- Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging (ECCV 2024 · similarity 0.90)
- Exploring Spatiotemporal Feature Propagation for Video-Level Compressive Spectral Reconstruction: Dataset, Model and Benchmark (CVPR 2026 · similarity 0.89)
- Unmixing Diffusion for Self-Supervised Hyperspectral Image Denoising (CVPR 2024 · similarity 0.88)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 2024 · similarity 0.86)
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.
