Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Esposito, Stefano, Chen, Anpei, Reiser, Christian, Bulò, Samuel Rota, Porzi, Lorenzo, Schwarz, Katja, Richardt, Christian, Zollhöfer, Michael, Kontschieder, Peter, Geiger, Andreas
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909554579603456
author Esposito, Stefano
Chen, Anpei
Reiser, Christian
Bulò, Samuel Rota
Porzi, Lorenzo
Schwarz, Katja
Richardt, Christian
Zollhöfer, Michael
Kontschieder, Peter
Geiger, Andreas
author_facet Esposito, Stefano
Chen, Anpei
Reiser, Christian
Bulò, Samuel Rota
Porzi, Lorenzo
Schwarz, Katja
Richardt, Christian
Zollhöfer, Michael
Kontschieder, Peter
Geiger, Andreas
contents High-quality view synthesis relies on volume rendering, splatting, or surface rendering. While surface rendering is typically the fastest, it struggles to accurately model fuzzy geometry like hair. In turn, alpha-blending techniques excel at representing fuzzy materials but require an unbounded number of samples per ray (P1). Further overheads are induced by empty space skipping in volume rendering (P2) and sorting input primitives in splatting (P3). We present a novel representation for real-time view synthesis where the (P1) number of sampling locations is small and bounded, (P2) sampling locations are efficiently found via rasterization, and (P3) rendering is sorting-free. We achieve this by representing objects as semi-transparent multi-layer meshes rendered in a fixed order. First, we model surface layers as signed distance function (SDF) shells with optimal spacing learned during training. Then, we bake them as meshes and fit UV textures. Unlike single-surface methods, our multi-layer representation effectively models fuzzy objects. In contrast to volume and splatting-based methods, our approach enables real-time rendering on low-power laptops and smartphones.
format Preprint
id arxiv_https___arxiv_org_abs_2409_02482
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes
Esposito, Stefano
Chen, Anpei
Reiser, Christian
Bulò, Samuel Rota
Porzi, Lorenzo
Schwarz, Katja
Richardt, Christian
Zollhöfer, Michael
Kontschieder, Peter
Geiger, Andreas
Computer Vision and Pattern Recognition
Graphics
Machine Learning
High-quality view synthesis relies on volume rendering, splatting, or surface rendering. While surface rendering is typically the fastest, it struggles to accurately model fuzzy geometry like hair. In turn, alpha-blending techniques excel at representing fuzzy materials but require an unbounded number of samples per ray (P1). Further overheads are induced by empty space skipping in volume rendering (P2) and sorting input primitives in splatting (P3). We present a novel representation for real-time view synthesis where the (P1) number of sampling locations is small and bounded, (P2) sampling locations are efficiently found via rasterization, and (P3) rendering is sorting-free. We achieve this by representing objects as semi-transparent multi-layer meshes rendered in a fixed order. First, we model surface layers as signed distance function (SDF) shells with optimal spacing learned during training. Then, we bake them as meshes and fit UV textures. Unlike single-surface methods, our multi-layer representation effectively models fuzzy objects. In contrast to volume and splatting-based methods, our approach enables real-time rendering on low-power laptops and smartphones.
title Volumetric Surfaces: Representing Fuzzy Geometries with Layered Meshes
topic Computer Vision and Pattern Recognition
Graphics
Machine Learning
url https://arxiv.org/abs/2409.02482