Reflectance and Natural Illumination from Single-Material Specular Objects Using Deep Learning

TLDR

The paper proposes a method to recover reflectance and illumination from a single image of a single‑material specular object under natural lighting. Using a data‑driven two‑step CNN pipeline, the authors first predict a reflectance map—either directly or via orientation‑based interpolation—and then reconstruct Phong reflectance parameters and high‑resolution spherical illumination maps, trained on large and newly introduced datasets. Extensive quantitative and qualitative tests on synthetic and real data demonstrate that the approach outperforms state‑of‑the‑art methods.

Abstract

In this paper, we present a method that estimates reflectance and illumination information from a single image depicting a single-material specular object from a given class under natural illumination. We follow a data-driven, learning-based approach trained on a very large dataset, but in contrast to earlier work we do not assume one or more components (shape, reflectance, or illumination) to be known. We propose a two-step approach, where we first estimate the object's reflectance map, and then further decompose it into reflectance and illumination. For the first step, we introduce a Convolutional Neural Network (CNN) that directly predicts a reflectance map from the input image itself, as well as an indirect scheme that uses additional supervision, first estimating surface orientation and afterwards inferring the reflectance map using a learning-based sparse data interpolation technique. For the second step, we suggest a CNN architecture to reconstruct both Phong reflectance parameters and high-resolution spherical illumination maps from the reflectance map. We also propose new datasets to train these CNNs. We demonstrate the effectiveness of our approach for both steps by extensive quantitative and qualitative evaluation in both synthetic and real data as well as through numerous applications, that show improvements over the state-of-the-art.