Saved in:
Bibliographic Details
Main Authors: S, Gabriel Pérez, Pérez, Juan C., Alfarra, Motasem, Zarzar, Jesús, Rojas, Sara, Ghanem, Bernard, Arbeláez, Pablo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.13135
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909294188822528
author S, Gabriel Pérez
Pérez, Juan C.
Alfarra, Motasem
Zarzar, Jesús
Rojas, Sara
Ghanem, Bernard
Arbeláez, Pablo
author_facet S, Gabriel Pérez
Pérez, Juan C.
Alfarra, Motasem
Zarzar, Jesús
Rojas, Sara
Ghanem, Bernard
Arbeláez, Pablo
contents This paper presents preliminary work on a novel connection between certified robustness in machine learning and the modeling of 3D objects. We highlight an intriguing link between the Maximal Certified Radius (MCR) of a classifier representing a space's occupancy and the space's Signed Distance Function (SDF). Leveraging this relationship, we propose to use the certification method of randomized smoothing (RS) to compute SDFs. Since RS' high computational cost prevents its practical usage as a way to compute SDFs, we propose an algorithm to efficiently run RS in low-dimensional applications, such as 3D space, by expressing RS' fundamental operations as Gaussian smoothing on pre-computed voxel grids. Our approach offers an innovative and practical tool to compute SDFs, validated through proof-of-concept experiments in novel view synthesis. This paper bridges two previously disparate areas of machine learning, opening new avenues for further exploration and potential cross-domain advancements.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13135
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Learning at the Intersection: Certified Robustness as a Tool for 3D Vision
S, Gabriel Pérez
Pérez, Juan C.
Alfarra, Motasem
Zarzar, Jesús
Rojas, Sara
Ghanem, Bernard
Arbeláez, Pablo
Computer Vision and Pattern Recognition
Artificial Intelligence
This paper presents preliminary work on a novel connection between certified robustness in machine learning and the modeling of 3D objects. We highlight an intriguing link between the Maximal Certified Radius (MCR) of a classifier representing a space's occupancy and the space's Signed Distance Function (SDF). Leveraging this relationship, we propose to use the certification method of randomized smoothing (RS) to compute SDFs. Since RS' high computational cost prevents its practical usage as a way to compute SDFs, we propose an algorithm to efficiently run RS in low-dimensional applications, such as 3D space, by expressing RS' fundamental operations as Gaussian smoothing on pre-computed voxel grids. Our approach offers an innovative and practical tool to compute SDFs, validated through proof-of-concept experiments in novel view synthesis. This paper bridges two previously disparate areas of machine learning, opening new avenues for further exploration and potential cross-domain advancements.
title Deep Learning at the Intersection: Certified Robustness as a Tool for 3D Vision
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2408.13135