Deep image-based Adaptive BRDF Measure

Wen Cao
10/3/2024
cs.GRcs.AI

No official code found. Best implementation: WenCao1101/Deep-image-based-Adaptive-BRDF-Measure (3 stars, last commit 2025-03-13).

Abstract

Efficient and accurate measurement of the bi-directional reflectance distribution function (BRDF) plays a key role in high quality image rendering and physically accurate sensor simulation. However, obtaining the reflectance properties of a material is both time-consuming and challenging. This paper presents a novel method for minimizing the number of samples required for high quality BRDF capture using a gonio-reflectometer setup. Taking an image of the physical material sample as input a lightweight neural network first estimates the parameters of an analytic BRDF model, and the distribution of the sample locations. In a second step we use an image based loss to find the number of samples required to meet the accuracy required. This approach significantly accelerates the measurement process while maintaining a high level of accuracy and fidelity in the BRDF representation.

View on arXivView PDF

Code Implementations(1)

WenCao1101/Deep-image-based-Adaptive-BRDF-MeasureCommunity100%

Example Code for Paper:Deep image-based Adaptive BRDF Measure https://arxiv.org/abs/2410.02917

30C++, PythonDec 29, 20241 years ago

Similar Papers

Physics-Based Decomposition of Reflectance and Shading using a Single Visible-Thermal Image Pair

83% match1 repo22025

Physically Based Neural Bidirectional Reflectance Distribution Function

81% match2024

Fast and accurate neural reflectance transformation imaging through knowledge distillation

81% match2 repos2025

On Neural BRDFs: A Thorough Comparison of State-of-the-Art Approaches

80% match2025

Neural BRDF Importance Sampling by Reparameterization

80% match1 repo202025

Neural Appearance Modeling From Single Images

80% match2024

Cite this paper

@article{cao2024deep,
  title  = {Deep image-based Adaptive BRDF Measure},
  author = {Wen Cao},
  year   = {2024},
  eprint = {2410.02917},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.02917v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.02917.svg)](https://codeofpaper.com/paper/2410.02917)

Discussion