NEURAL VIEW-DEPENDENT PRINCIPLED BRDF ADAPTER

Number: 20260311423
Published: 2026-10-08
Filed: 2026-04-02
Assignee: Disney Enterprises, Inc.
Inventors: SHARMA; Rajesh, WEISS; Sebastian Klaus, PORTENIER; Tiziano Andrea, PAPAS; Marios
CPC: G06T15/506; G06T15/20
Verdict: Low Notable software
First reported: 2026-W41 (2026-10-08)
Source: Google Patents · FreePatentsOnline

The keeper's note

Trains a neural network to adapt one material's light-reflecting properties to mimic another from any viewing angle -- a shortcut for realistic material rendering in CG.

Abstract

A neural network-based method and system are disclosed for adapting parameters of a source bidirectional reflectance distribution function (BRDF) to a target BRDF, enabling efficient and expressive material rendering. Some aspects include generating or receiving BRDF data for a plurality of source materials as a function of incoming and outgoing light directions, aggregating the data into a representation suitable for machine learning, and training a neural network to map source BRDF parameters and viewing direction to target BRDF parameters. The trained network is used to predict target BRDF parameters, which are supplied to a rendering engine for visualization. The approach supports both measured and simulated materials, employs flexible data aggregation strategies such as uniform or adaptive binning, and may utilize encoder-decoder architectures for multi-material adaptation and can thus achieve visual fidelity of complex materials while maintaining compatibility with existing parametric rendering systems, facilitating efficient, view-dependent rendering for diverse applications.

Background

BACKGROUND

Models that attempt to simulate light and material interaction can be broadly classified into two main categories: (1) non-neural parametric models, and (2) neural methods that learn from material data.

Non-neural parametric models attempt to simulate light and material interaction using physical properties of materials often approximating the material surface as a microfacet model. For data from measured materials, non-neural methods use techniques like Principle Component Analysis (PCA) or other optimization methods to map measured data as closely as possible to existing parametric models. Parametric appearance models currently used in production can be very efficient to evaluate and sample but are limited in terms of capturing complex appearance (e.g., multi-layer materials, measured materials, etc.) for which additional parameters and computation may be needed. Moreover, creating and adding new appearance models to existing production renderers is non-trivial and introduces additional parameters and complexity for artists.

Current neural methods collect data from an existing parametric model or utilize directly measured data and learn the bidirectional reflectance distribution function (BRDF) of the material using a neural process. Fully neural appearance models can be more expressive than existing parametric models, but they are computationally expensive and slow to evaluate and sample efficiently, especially on CPUs on which many producti

Claims

1. A method for adapting a source bidirectional reflectance distribution function (BRDF) to a target BRDF using a neural network, the method comprising: generating data for a plurality of source materials including measured or simulated BRDF values; aggregating the generated data into a multi-dimensional representation of incoming and outgoing light directions; training a neural network to map source BRDF parameters and viewing direction to target BRDF parameters; conditioning the neural network on source BRDF control parameters and viewing direction; predicting parameters of the target BRDF for rendering purposes; and rendering the material using the predicted target BRDF parameters in an existing rendering engine. || 9. A system for neural view-dependent adaptation of BRDF parameters comprising: a data generation module configured to simulate or measure material BRDFs; an aggregation module configured to organize data into multi-dimensional bins; a neural network module configured to map source BRDF parameters and viewing direction to target BRDF parameters; an encoder-decoder architecture for handling multiple materials; and a rendering engine configured to render materials using the predicted target BRDF parameters. || 16. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform a method for neural view-dependent BRDF adaptation, the method comprising: receiving source BRDF data; aggregating data into bins based on incoming and outgoing directions; training a neural network to map source parameters and viewing direction to target BRDF parameters; and predicting target BRDF parameters for rendering.