Neural reflectance transformation imaging
Open Access
- 17 July 2020
- journal article
- research article
- Published by Springer Nature in The Visual Computer
- Vol. 36 (10-12) , 2161-2174
Abstract
Reflectance transformation imaging (RTI) is a computational photography technique widely used in the cultural heritage and material science domains to characterize relieved surfaces. It basically consists of capturing multiple images from a fixed viewpoint with varying lights. Handling the potentially huge amount of information stored in an RTI acquisition that consists typically of 50–100 RGB values per pixel, allowing data exchange, interactive visualization, and material analysis, is not easy. The solution used in practical applications consists of creating “relightable images” by approximating the pixel information with a function of the light direction, encoded with a small number of parameters. This encoding allows the estimation of images relighted from novel, arbitrary lights, with a quality that, however, is not always satisfactory. In this paper, we present NeuralRTI, a framework for pixel-based encoding and relighting of RTI data. Using a simple autoencoder architecture, we show that it is possible to obtain a highly compressed representation that better preserves the original information and provides increased quality of virtual images relighted from novel directions, especially in the case of challenging glossy materials. We also address the problem of validating the relight quality on different surfaces, proposing a specific benchmark, SynthRTI, including image collections synthetically created with physical-based rendering and featuring objects with different materials and geometric complexity. On this dataset and as well on a collection of real acquisitions performed on heterogeneous surfaces, we demonstrate the advantages of the proposed relightable image encoding.Keywords
Funding Information
- Ministero dell’Istruzione, dell’Università e della Ricerca
This publication has 18 references indexed in Scilit:
- A novel framework for highlight reflectance transformation imagingComputer Vision and Image Understanding, 2018
- Discrete Modal Decomposition: a new approach for the reflectance modeling and rendering of real surfacesMachine Vision and Applications, 2017
- LLNet: A deep autoencoder approach to natural low-light image enhancementPattern Recognition, 2017
- A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo2016
- Image based relighting using neural networksACM Transactions on Graphics, 2015
- Discrete Modal Decomposition for surface appearance modelling and rendering2015
- Dynamic shading enhancement for reflectance transformation imagingJournal on Computing and Cultural Heritage, 2010
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Polynomial texture maps2001