Photometric Stereo using Gaussian Splatting and inverse rendering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ducastel, Matéo, Tschumperlé, David, Quéau, Yvain
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918087324860416
author Ducastel, Matéo
Tschumperlé, David
Quéau, Yvain
author_facet Ducastel, Matéo
Tschumperlé, David
Quéau, Yvain
contents Recent state-of-the-art algorithms in photometric stereo rely on neural networks and operate either through prior learning or inverse rendering optimization. Here, we revisit the problem of calibrated photometric stereo by leveraging recent advances in 3D inverse rendering using the Gaussian Splatting formalism. This allows us to parameterize the 3D scene to be reconstructed and optimize it in a more interpretable manner. Our approach incorporates a simplified model for light representation and demonstrates the potential of the Gaussian Splatting rendering engine for the photometric stereo problem.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06684
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Photometric Stereo using Gaussian Splatting and inverse rendering
Ducastel, Matéo
Tschumperlé, David
Quéau, Yvain
Image and Video Processing
Artificial Intelligence
Recent state-of-the-art algorithms in photometric stereo rely on neural networks and operate either through prior learning or inverse rendering optimization. Here, we revisit the problem of calibrated photometric stereo by leveraging recent advances in 3D inverse rendering using the Gaussian Splatting formalism. This allows us to parameterize the 3D scene to be reconstructed and optimize it in a more interpretable manner. Our approach incorporates a simplified model for light representation and demonstrates the potential of the Gaussian Splatting rendering engine for the photometric stereo problem.
title Photometric Stereo using Gaussian Splatting and inverse rendering
topic Image and Video Processing
Artificial Intelligence
url https://arxiv.org/abs/2507.06684