Intrinsic Image Fusion for Multi-View 3D Material Reconstruction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kocsis, Peter, Höllein, Lukas, Nießner, Matthias
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914412667863040
author Kocsis, Peter
Höllein, Lukas
Nießner, Matthias
author_facet Kocsis, Peter
Höllein, Lukas
Nießner, Matthias
contents We introduce Intrinsic Image Fusion, a method that reconstructs high-quality physically based materials from multi-view images. Material reconstruction is highly underconstrained and typically relies on analysis-by-synthesis, which requires expensive and noisy path tracing. To better constrain the optimization, we incorporate single-view priors into the reconstruction process. We leverage a diffusion-based material estimator that produces multiple, but often inconsistent, candidate decompositions per view. To reduce the inconsistency, we fit an explicit low-dimensional parametric function to the predictions. We then propose a robust optimization framework using soft per-view prediction selection together with confidence-based soft multi-view inlier set to fuse the most consistent predictions of the most confident views into a consistent parametric material space. Finally, we use inverse path tracing to optimize for the low-dimensional parameters. Our results outperform state-of-the-art methods in material disentanglement on both synthetic and real scenes, producing sharp and clean reconstructions suitable for high-quality relighting.
format Preprint
id arxiv_https___arxiv_org_abs_2512_13157
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Intrinsic Image Fusion for Multi-View 3D Material Reconstruction
Kocsis, Peter
Höllein, Lukas
Nießner, Matthias
Computer Vision and Pattern Recognition
Artificial Intelligence
I.4.8; I.4.9; I.2.10
We introduce Intrinsic Image Fusion, a method that reconstructs high-quality physically based materials from multi-view images. Material reconstruction is highly underconstrained and typically relies on analysis-by-synthesis, which requires expensive and noisy path tracing. To better constrain the optimization, we incorporate single-view priors into the reconstruction process. We leverage a diffusion-based material estimator that produces multiple, but often inconsistent, candidate decompositions per view. To reduce the inconsistency, we fit an explicit low-dimensional parametric function to the predictions. We then propose a robust optimization framework using soft per-view prediction selection together with confidence-based soft multi-view inlier set to fuse the most consistent predictions of the most confident views into a consistent parametric material space. Finally, we use inverse path tracing to optimize for the low-dimensional parameters. Our results outperform state-of-the-art methods in material disentanglement on both synthetic and real scenes, producing sharp and clean reconstructions suitable for high-quality relighting.
title Intrinsic Image Fusion for Multi-View 3D Material Reconstruction
topic Computer Vision and Pattern Recognition
Artificial Intelligence
I.4.8; I.4.9; I.2.10
url https://arxiv.org/abs/2512.13157