NeuBTF: Neural fields for BTF encoding and transfer

TL;DR

NeuBTF introduces a neural material representation that enables flexible, high-quality encoding, transfer, and extrapolation of BTFs, overcoming limitations of previous fixed neural models, with efficient compression and broad applicability.

Contribution

It proposes a novel neural BTF representation that supports tiling, extrapolation, and transfer, addressing limitations of existing neural material models.

Findings

Achieves competitive compression rates for neural BTFs.

Demonstrates generality across synthetic and captured materials.

Enables BTF transfer conditioned on input images.

Abstract

Neural material representations are becoming a popular way to represent materials for rendering. They are more expressive than analytic models and occupy less memory than tabulated BTFs. However, existing neural materials are immutable, meaning that their output for a certain query of UVs, camera, and light vector is fixed once they are trained. While this is practical when there is no need to edit the material, it can become very limiting when the fragment of the material used for training is too small or not tileable, which frequently happens when the material has been captured with a gonioreflectometer. In this paper, we propose a novel neural material representation which jointly tackles the problems of BTF compression, tiling, and extrapolation. At test time, our method uses a guidance image as input to condition the neural BTF to the structural features of this input image. Then, the neural BTF can be queried as a regular BTF using UVs, camera, and light vectors. Every component in our framework is purposefully designed to maximize BTF encoding quality at minimal parameter count and computational complexity, achieving competitive compression rates compared with previous work. We demonstrate the results of our method on a variety of synthetic and captured materials, showing its generality and capacity to learn to represent many optical properties.