Search papers, labs, and topics across Lattice.
This paper presents a novel approach to hyperspectral intrinsic decomposition (HID) that effectively disentangles reflectance and photometric components in non-Lambertian scenes by reformulating the recovery process into the estimation of spectral-spatial target variables. The authors introduce a dual-scale decomposition scheme that utilizes photometrically invariant descriptors and specularity-guided attention to enhance boundary preservation and refine specularity-dominated regions. Their method is validated through extensive experiments on a newly established dataset, CITE, showcasing significant improvements in handling diverse real-world imaging scenarios compared to existing techniques.
Non-Lambertian scenes can now be accurately decomposed into reflectance and photometric components without auxiliary inputs, revolutionizing hyperspectral imaging analysis.
Hyperspectral intrinsic decomposition (HID) aims to disentangle material-related spectral properties and photometric effects in hyperspectral images (HSIs), which is essential for understanding real-world imaging processes and benefits a variety of downstream applications. Most existing HID studies have been developed under Lambertian or near-Lambertian assumptions. The few prior non-Lambertian efforts rely on simplified specular assumptions insufficient to handle diverse real-world specularity, and typically require auxiliary inputs or recover only a subset of the coupled reflectance and photometric components, hindering complete and blind decomposition. In this paper, we revisit the dichromatic reflection model (DRM) and develop a unified inversion paradigm that reformulates the recovery of four coupled reflectance and photometric components as the estimation of two spectral--spatial target variables. Building on this reformulation, we propose a dual-scale decomposition scheme to handle non-Lambertian effects with distinct spatial characteristics. At the global scale, photometrically invariant descriptors serve as edge priors for high-fidelity intrinsic boundary preservation; at the local scale, specularity-guided attention directs refinement with emphasis on specularity-dominated regions, including those affected by clipping distortion. To facilitate future research, we establish CITE, the first public real-world HID dataset for non-Lambertian objects, and develop a Physically-faithful Intrinsic Set Generator (PISG) for controllable data synthesis. Extensive ablation studies and experiments on the CITE and additional HSIs demonstrate the effectiveness of our method and its robustness across diverse scenes.
