Deep Dual Loss BRDF Parameter Estimation (Unknown language)

In: Workshop on Material Appearance Modeling   ;  41-44  ;  2018

How to get this document?

Download
Commercial Copyright fee: €14.50 Basic fee: €4.00 Total price: €18.50
Academic Copyright fee: €4.50 Basic fee: €2.00 Total price: €6.50

Surface parameter estimation is an essential field in computer games and movies. An exact representation of a real-world surface allows for a higher degree of realism. Capturing or artistically creating these materials is a time-consuming process. We propose a method which utilizes an encoder-decoder Convolutional Neural Network (CNN) to extract parameters for the Bidirectional Reflectance Distribution Function (BRDF) automatically from a sparse sample set. This is done by implementing a differentiable renderer, which allows for a loss backpropagation of rendered images. This photometric loss is essential because defining a numerical BRDF distance metric is difficult. A second loss is added, which compares the parameters maps directly. Therefore, the statistical properties of the BRDF model are learned, which reduces artifacts in the predicted parameters. This dual loss principal improves the result of the network significantly. Opposed to previous means this method retrieves information of the whole surface as spatially varying BRDF (SVBRDF) parameters with a sufficiently high resolution for intended real-world usage. The capture process for materials only requires five known light positions with a fixed camera position. This reduces the scanning time drastically, and a material sample can be obtained in seconds with an automated system.

Table of contents conference proceedings

The tables of contents are generated automatically and are based on the data records of the individual contributions available in the index of the TIB portal. The display of the Tables of Contents may therefore be incomplete.

1
ICL Multispectral Light Stage: Building a Versatile LED Sphere with Off-the-shelf Components
Kampouris, Christos / Ghosh, Abhijeet | 2018
5
On the Advancement of BTF Measurement on Site
Havran, Vlastimil / Hosek, Jan / Nemcova, Sarka / Cap, Jiri | 2018
11
Iso Photographic Rendering
Porral, Philippe / Lucas, Laurent / Muller, Thomas / Randrianandrasana, Joël | 2018
15
A Simple Diffuse Fluorescent BBRRDF Model
Jung, Alisa / Hanika, Johannes / Marschner, Steve / Dachsbacher, Carsten | 2018
19
Image-based Fitting of Procedural Yarn Models
Saalfeld, Alina / Reibold, Florian / Dachsbacher, Carsten | 2018
23
Towards Practical Rendering of Fiber-Level Cloth Appearance Models
Alejandre, Adrian / Aliaga, Carlos / Marco, Julio / Jarabo, Adrian / Muñoz, Adolfo | 2018
27
A Method for Fitting Measured Car Paints to a Game Engine's Rendering Model
Kneiphof, Tom / Golla, Tim / Weinmann, Michael / Klein, Reinhard | 2018
33
Perception of Car Shape Orientation and Anisotropy Alignment
Filip, Jiri / Kolafová, Martina | 2018
37
Towards Physically Based Material Appearance in the Thermal Infrared Spectrum: A Short Survey
Haraké, Laura / Burkard, Eva | 2018
41
Deep Dual Loss BRDF Parameter Estimation
Boss, Mark / Groh, Fabian / Herholz, Sebastian / Lensch, Hendrik P. A. | 2018
45
Towards a Principled Kernel Prediction for Spatially Varying BSSRDFs
Elek, Oskar / Krivánek, Jaroslav | 2018
Feedback