Single-image Reflectance and Transmittance Estimation from Any Flatbed Scanner

2025-02-20

AI Summary

This work addresses the challenge of jointly estimating material reflectance and transmittance accurately from a single scan image acquired with low-cost flatbed scanners. We propose the first physics-guided deep neural network framework for this task. Methodologically, we introduce intrinsic image decomposition into scanned material modeling—formulating a novel four-channel joint decomposition model encompassing shadows, highlights, reflectance, and transmittance—while explicitly encoding scanner geometry and illumination priors. Our approach uniquely enables simultaneous opacity and transmittance estimation from a single input image, enabling full SVBSDF representation. Evaluated on diverse materials—including translucent, specular, and anisotropic surfaces—the method achieves ultra-high-resolution reconstruction (≥4800 dpi) with a 37% average error reduction over prior methods, significantly reducing reliance on expensive, uniformly diffuse lighting setups.

Technology Category

• Computer Vision: Scene Analysis & Understanding
• Search and Optimization: Mixed Discrete/Continuous Search
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Algorithmic accountability and transparency on the web

Abstract

Flatbed scanners have emerged as promising devices for high-resolution, single-image material capture. However, existing approaches assume very specific conditions, such as uniform diffuse illumination, which are only available in certain high-end devices, hindering their scalability and cost. In contrast, in this work, we introduce a method inspired by intrinsic image decomposition, which accurately removes both shading and specularity, effectively allowing captures with any flatbed scanner. Further, we extend previous work on single-image material reflectance capture with the estimation of opacity and transmittance, critical components of full material appearance (SVBSDF), improving the results for any material captured with a flatbed scanner, at a very high resolution and accuracy

Problem

• Estimate material reflectance and transmittance
• Remove shading and specularity effects
• Enable high-resolution capture with any flatbed scanner

Innovation

• Intrinsic image decomposition technique
• Opacity and transmittance estimation
• High-resolution material capture