Saved in:
Bibliographic Details
Main Authors: Petit, Doriand, Bourgeois, Steve, Pavel, Dumitru, Gay-Bellile, Vincent, Chabot, Florian, Barthe, Loic
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.03357
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910529893695488
author Petit, Doriand
Bourgeois, Steve
Pavel, Dumitru
Gay-Bellile, Vincent
Chabot, Florian
Barthe, Loic
author_facet Petit, Doriand
Bourgeois, Steve
Pavel, Dumitru
Gay-Bellile, Vincent
Chabot, Florian
Barthe, Loic
contents Recent advances in Neural Fields mostly rely on developing task-specific supervision which often complicates the models. Rather than developing hard-to-combine and specific modules, another approach generally overlooked is to directly inject generic priors on the scene representation (also called inductive biases) into the NeRF architecture. Based on this idea, we propose the RING-NeRF architecture which includes two inductive biases : a continuous multi-scale representation of the scene and an invariance of the decoder's latent space over spatial and scale domains. We also design a single reconstruction process that takes advantage of those inductive biases and experimentally demonstrates on-par performances in terms of quality with dedicated architecture on multiple tasks (anti-aliasing, few view reconstruction, SDF reconstruction without scene-specific initialization) while being more efficient. Moreover, RING-NeRF has the distinctive ability to dynamically increase the resolution of the model, opening the way to adaptive reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2312_03357
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle RING-NeRF : Rethinking Inductive Biases for Versatile and Efficient Neural Fields
Petit, Doriand
Bourgeois, Steve
Pavel, Dumitru
Gay-Bellile, Vincent
Chabot, Florian
Barthe, Loic
Computer Vision and Pattern Recognition
Recent advances in Neural Fields mostly rely on developing task-specific supervision which often complicates the models. Rather than developing hard-to-combine and specific modules, another approach generally overlooked is to directly inject generic priors on the scene representation (also called inductive biases) into the NeRF architecture. Based on this idea, we propose the RING-NeRF architecture which includes two inductive biases : a continuous multi-scale representation of the scene and an invariance of the decoder's latent space over spatial and scale domains. We also design a single reconstruction process that takes advantage of those inductive biases and experimentally demonstrates on-par performances in terms of quality with dedicated architecture on multiple tasks (anti-aliasing, few view reconstruction, SDF reconstruction without scene-specific initialization) while being more efficient. Moreover, RING-NeRF has the distinctive ability to dynamically increase the resolution of the model, opening the way to adaptive reconstruction.
title RING-NeRF : Rethinking Inductive Biases for Versatile and Efficient Neural Fields
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.03357