A Dynamic By-example BTF Synthesis Scheme

TL;DR

This paper introduces a fully dynamic 6D BTF synthesis method that enables on-the-fly rendering of large, non-repetitive textures by decomposing BTFs into low-dimensional components and querying them during rendering.

Contribution

The proposed scheme allows real-time, on-demand synthesis of dynamic BTFs without pre-generation, leveraging neural dimension reduction and lightweight MLPs.

Findings

Enables efficient, on-the-fly rendering of large BTFs.

Reduces storage and pre-computation requirements.

Demonstrates effectiveness on various BTF datasets.

Abstract

Measured Bidirectional Texture Function (BTF) can faithfully reproduce a realistic appearance but is costly to acquire and store due to its 6D nature (2D spatial and 4D angular). Therefore, it is practical and necessary for rendering to synthesize BTFs from a small example patch. While previous methods managed to produce plausible results, we find that they seldomly take into consideration the property of being dynamic, so a BTF must be synthesized before the rendering process, resulting in limited size, costly pre-generation and storage issues. In this paper, we propose a dynamic BTF synthesis scheme, where a BTF at any position only needs to be synthesized when being queried. Our insight is that, with the recent advances in neural dimension reduction methods, a BTF can be decomposed into disjoint low-dimensional components. We can perform dynamic synthesis only on the positional dimensions, and during rendering, recover the BTF by querying and combining these low-dimensional functions with the help of a lightweight Multilayer Perceptron (MLP). Consequently, we obtain a fully dynamic 6D BTF synthesis scheme that does not require any pre-generation, which enables efficient rendering of our infinitely large and non-repetitive BTFs on the fly. We demonstrate the effectiveness of our method through various types of BTFs taken from UBO2014.