Towards Fast and Scalable Normal Integration using Continuous Components

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Milano, Francesco, Chung, Jen Jen, Ott, Lionel, Siegwart, Roland
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911295906775040
author Milano, Francesco
Chung, Jen Jen
Ott, Lionel
Siegwart, Roland
author_facet Milano, Francesco
Chung, Jen Jen
Ott, Lionel
Siegwart, Roland
contents Surface normal integration is a fundamental problem in computer vision, dealing with the objective of reconstructing a surface from its corresponding normal map. Existing approaches require an iterative global optimization to jointly estimate the depth of each pixel, which scales poorly to larger normal maps. In this paper, we address this problem by recasting normal integration as the estimation of relative scales of continuous components. By constraining pixels belonging to the same component to jointly vary their scale, we drastically reduce the number of optimization variables. Our framework includes a heuristic to accurately estimate continuous components from the start, a strategy to rebalance optimization terms, and a technique to iteratively merge components to further reduce the size of the problem. Our method achieves state-of-the-art results on the standard normal integration benchmark in as little as a few seconds and achieves one-order-of-magnitude speedup over pixel-level approaches on large-resolution normal maps.
format Preprint
id arxiv_https___arxiv_org_abs_2510_11508
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Fast and Scalable Normal Integration using Continuous Components
Milano, Francesco
Chung, Jen Jen
Ott, Lionel
Siegwart, Roland
Computer Vision and Pattern Recognition
Surface normal integration is a fundamental problem in computer vision, dealing with the objective of reconstructing a surface from its corresponding normal map. Existing approaches require an iterative global optimization to jointly estimate the depth of each pixel, which scales poorly to larger normal maps. In this paper, we address this problem by recasting normal integration as the estimation of relative scales of continuous components. By constraining pixels belonging to the same component to jointly vary their scale, we drastically reduce the number of optimization variables. Our framework includes a heuristic to accurately estimate continuous components from the start, a strategy to rebalance optimization terms, and a technique to iteratively merge components to further reduce the size of the problem. Our method achieves state-of-the-art results on the standard normal integration benchmark in as little as a few seconds and achieves one-order-of-magnitude speedup over pixel-level approaches on large-resolution normal maps.
title Towards Fast and Scalable Normal Integration using Continuous Components
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.11508