Objective, Absolute and Hue-aware Metrics for Intrinsic Image Decomposition on Real-World Scenes: A Proof of Concept

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sato, Shogo, Tsuchida, Masaru, Yamaguchi, Mariko, Kaneko, Takuhiro, Murasaki, Kazuhiko, Yoshida, Taiga, Tanida, Ryuichi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909623055810560
author Sato, Shogo
Tsuchida, Masaru
Yamaguchi, Mariko
Kaneko, Takuhiro
Murasaki, Kazuhiko
Yoshida, Taiga
Tanida, Ryuichi
author_facet Sato, Shogo
Tsuchida, Masaru
Yamaguchi, Mariko
Kaneko, Takuhiro
Murasaki, Kazuhiko
Yoshida, Taiga
Tanida, Ryuichi
contents 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. )
format Preprint
id arxiv_https___arxiv_org_abs_2505_19500
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Objective, Absolute and Hue-aware Metrics for Intrinsic Image Decomposition on Real-World Scenes: A Proof of Concept
Sato, Shogo
Tsuchida, Masaru
Yamaguchi, Mariko
Kaneko, Takuhiro
Murasaki, Kazuhiko
Yoshida, Taiga
Tanida, Ryuichi
Computer Vision and Pattern Recognition
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. )
title Objective, Absolute and Hue-aware Metrics for Intrinsic Image Decomposition on Real-World Scenes: A Proof of Concept
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.19500