Spatially-Adaptive Hash Encodings For Neural Surface Reconstruction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Walker, Thomas, Mariotti, Octave, Vaxman, Amir, Bilen, Hakan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910731262230528
author Walker, Thomas
Mariotti, Octave
Vaxman, Amir
Bilen, Hakan
author_facet Walker, Thomas
Mariotti, Octave
Vaxman, Amir
Bilen, Hakan
contents Positional encodings are a common component of neural scene reconstruction methods, and provide a way to bias the learning of neural fields towards coarser or finer representations. Current neural surface reconstruction methods use a "one-size-fits-all" approach to encoding, choosing a fixed set of encoding functions, and therefore bias, across all scenes. Current state-of-the-art surface reconstruction approaches leverage grid-based multi-resolution hash encoding in order to recover high-detail geometry. We propose a learned approach which allows the network to choose its encoding basis as a function of space, by masking the contribution of features stored at separate grid resolutions. The resulting spatially adaptive approach allows the network to fit a wider range of frequencies without introducing noise. We test our approach on standard benchmark surface reconstruction datasets and achieve state-of-the-art performance on two benchmark datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05179
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Spatially-Adaptive Hash Encodings For Neural Surface Reconstruction
Walker, Thomas
Mariotti, Octave
Vaxman, Amir
Bilen, Hakan
Computer Vision and Pattern Recognition
Positional encodings are a common component of neural scene reconstruction methods, and provide a way to bias the learning of neural fields towards coarser or finer representations. Current neural surface reconstruction methods use a "one-size-fits-all" approach to encoding, choosing a fixed set of encoding functions, and therefore bias, across all scenes. Current state-of-the-art surface reconstruction approaches leverage grid-based multi-resolution hash encoding in order to recover high-detail geometry. We propose a learned approach which allows the network to choose its encoding basis as a function of space, by masking the contribution of features stored at separate grid resolutions. The resulting spatially adaptive approach allows the network to fit a wider range of frequencies without introducing noise. We test our approach on standard benchmark surface reconstruction datasets and achieve state-of-the-art performance on two benchmark datasets.
title Spatially-Adaptive Hash Encodings For Neural Surface Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.05179