Objective, Absolute and Hue-aware Metrics for Intrinsic Image Decomposition on Real-World Scenes: A Proof of Concept
This work addresses the challenge of assessing IID quality for researchers in computer vision, but it is incremental as it is a proof of concept verified only in a laboratory environment.
The paper tackled the problem of quantitatively evaluating intrinsic image decomposition (IID) in real-world scenes by proposing a concept using hyperspectral imaging and LiDAR intensity to calculate albedo, and suggested its feasibility for objective, absolute, and hue-aware assessment.
Intrinsic image decomposition (IID) is the task of separating an image into albedo and shade. In real-world scenes, it is difficult to quantitatively assess IID quality due to the unavailability of ground truth. The existing method provides the relative reflection intensities based on human-judged annotations. However, these annotations have challenges in subjectivity, relative evaluation, and hue non-assessment. To address these, we propose a concept of quantitative evaluation with a calculated albedo from a hyperspectral imaging and light detection and ranging (LiDAR) intensity. Additionally, we introduce an optional albedo densification approach based on spectral similarity. This paper conducted a concept verification in a laboratory environment, and suggested the feasibility of an objective, absolute, and hue-aware assessment. (This paper is accepted by IEEE ICIP 2025. )