Fine-Grained Spatially Varying Material Selection in Images

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Guerrero-Viu, Julia, Fischer, Michael, Georgiev, Iliyan, Garces, Elena, Gutierrez, Diego, Masia, Belen, Deschaintre, Valentin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915336523087872
author Guerrero-Viu, Julia
Fischer, Michael
Georgiev, Iliyan
Garces, Elena
Gutierrez, Diego
Masia, Belen
Deschaintre, Valentin
author_facet Guerrero-Viu, Julia
Fischer, Michael
Georgiev, Iliyan
Garces, Elena
Gutierrez, Diego
Masia, Belen
Deschaintre, Valentin
contents Selection is the first step in many image editing processes, enabling faster and simpler modifications of all pixels sharing a common modality. In this work, we present a method for material selection in images, robust to lighting and reflectance variations, which can be used for downstream editing tasks. We rely on vision transformer (ViT) models and leverage their features for selection, proposing a multi-resolution processing strategy that yields finer and more stable selection results than prior methods. Furthermore, we enable selection at two levels: texture and subtexture, leveraging a new two-level material selection (DuMaS) dataset which includes dense annotations for over 800,000 synthetic images, both on the texture and subtexture levels.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09023
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fine-Grained Spatially Varying Material Selection in Images
Guerrero-Viu, Julia
Fischer, Michael
Georgiev, Iliyan
Garces, Elena
Gutierrez, Diego
Masia, Belen
Deschaintre, Valentin
Graphics
Computer Vision and Pattern Recognition
Selection is the first step in many image editing processes, enabling faster and simpler modifications of all pixels sharing a common modality. In this work, we present a method for material selection in images, robust to lighting and reflectance variations, which can be used for downstream editing tasks. We rely on vision transformer (ViT) models and leverage their features for selection, proposing a multi-resolution processing strategy that yields finer and more stable selection results than prior methods. Furthermore, we enable selection at two levels: texture and subtexture, leveraging a new two-level material selection (DuMaS) dataset which includes dense annotations for over 800,000 synthetic images, both on the texture and subtexture levels.
title Fine-Grained Spatially Varying Material Selection in Images
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.09023