ICTPolarReal: A Polarized Reflection and Material Dataset of Real World Objects

2026-03-25

AI Summary

This work addresses the challenge of modeling real-world material reflectance, which is hindered by the scarcity of measured data and the reliance of existing methods on synthetic data captured under simplified lighting conditions that fail to generalize to real images. To overcome this limitation, we present the first large-scale dataset of polarized reflectance and material properties from real objects, captured using a Light Stage system equipped with 8 cameras and 346 light sources. Our setup acquires over 1.2 million high-resolution images under five-dimensional conditions—multiple viewpoints, illumination directions, and polarization states—enabling, for the first time, physically accurate diffuse–specular separation on real objects. By leveraging cross- and parallel-polarized illumination, a polarized reflectance decomposition algorithm, and analytical estimation of albedo and surface normals, our approach significantly improves material accuracy, lighting fidelity, and geometric consistency in intrinsic image decomposition, relighting, and sparse-view 3D reconstruction for both inverse and forward rendering.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Data transparency and provenance
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Accurately modeling how real-world materials reflect light remains a core challenge in inverse rendering, largely due to the scarcity of real measured reflectance data. Existing approaches rely heavily on synthetic datasets with simplified illumination and limited material realism, preventing models from generalizing to real-world images. We introduce a large-scale polarized reflection and material dataset of real-world objects, captured with an 8-camera, 346-light Light Stage equipped with cross/parallel polarization. Our dataset spans 218 everyday objects across five acquisition dimensions-multiview, multi-illumination, polarization, reflectance separation, and material attributes-yielding over 1.2M high-resolution images with diffuse-specular separation and analytically derived diffuse albedo, specular albedo, and surface normals. Using this dataset, we train and evaluate state-of-the-art inverse and forward rendering models on intrinsic decomposition, relighting, and sparse-view 3D reconstruction, demonstrating significant improvements in material separation, illumination fidelity, and geometric consistency. We hope that our work can establish a new foundation for physically grounded material understanding and enable real-world generalization beyond synthetic training regimes. Project page: https://jingyangcarl.github.io/ICTPolarReal/

Problem

• inverse rendering
• real-world reflectance
• material modeling
• polarized reflection
• dataset scarcity

Innovation

• polarized reflection
• real-world material dataset
• inverse rendering
• diffuse-specular separation
• Light Stage