Material Transforms from Disentangled NeRF Representations

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lopes, Ivan, Lalonde, Jean-François, de Charette, Raoul
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913576700084224
author Lopes, Ivan
Lalonde, Jean-François
de Charette, Raoul
author_facet Lopes, Ivan
Lalonde, Jean-François
de Charette, Raoul
contents In this paper, we first propose a novel method for transferring material transformations across different scenes. Building on disentangled Neural Radiance Field (NeRF) representations, our approach learns to map Bidirectional Reflectance Distribution Functions (BRDF) from pairs of scenes observed in varying conditions, such as dry and wet. The learned transformations can then be applied to unseen scenes with similar materials, therefore effectively rendering the transformation learned with an arbitrary level of intensity. Extensive experiments on synthetic scenes and real-world objects validate the effectiveness of our approach, showing that it can learn various transformations such as wetness, painting, coating, etc. Our results highlight not only the versatility of our method but also its potential for practical applications in computer graphics. We publish our method implementation, along with our synthetic/real datasets on https://github.com/astra-vision/BRDFTransform
format Preprint
id arxiv_https___arxiv_org_abs_2411_08037
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Material Transforms from Disentangled NeRF Representations
Lopes, Ivan
Lalonde, Jean-François
de Charette, Raoul
Computer Vision and Pattern Recognition
Graphics
In this paper, we first propose a novel method for transferring material transformations across different scenes. Building on disentangled Neural Radiance Field (NeRF) representations, our approach learns to map Bidirectional Reflectance Distribution Functions (BRDF) from pairs of scenes observed in varying conditions, such as dry and wet. The learned transformations can then be applied to unseen scenes with similar materials, therefore effectively rendering the transformation learned with an arbitrary level of intensity. Extensive experiments on synthetic scenes and real-world objects validate the effectiveness of our approach, showing that it can learn various transformations such as wetness, painting, coating, etc. Our results highlight not only the versatility of our method but also its potential for practical applications in computer graphics. We publish our method implementation, along with our synthetic/real datasets on https://github.com/astra-vision/BRDFTransform
title Material Transforms from Disentangled NeRF Representations
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2411.08037