Neural reflectance transformation imaging
- PDF / 3,341,647 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 85 Downloads / 213 Views
ORIGINAL ARTICLE
Neural reflectance transformation imaging Tinsae G. Dulecha1
· Filippo A. Fanni1 · Federico Ponchio2 · Fabio Pellacini3 · Andrea Giachetti1
© The Author(s) 2020
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 Reflectance transformation imaging · Relighting · Neural network · Autoencoder · Benchmark
1 Introduction Reflectance transformation imaging [4,9,11] is a popular computational photography technique, allowing to capture the rich representations of surfaces including geometric details and local reflective behavior of materials. It consists
B
Tinsae G. Dulecha [email protected] Filippo A. Fanni [email protected] Federico Ponchio [email protected] Fabio Pellacini [email protected] Andrea Giachetti [email protected]
1
Department of Computer Science, University of Verona, Verona, Italy
2
ISTI-CNR, Pisa, Italy
3
Sapienza University of Rome, Rome, Italy
of capturing sets of images from a fixed point of view with varying light direction (and in some cases varying light wavelengths). These sets are often referred to also as multi-light image collections (MLIC). A recent survey [14] shows that there is a large number of applications exploiting interactive relighting and feature extraction from this kind of data, in different fields like cultural heritage, material science, archaeology, quality contr
Data Loading...
