AiSDF: Structure-aware Neural Signed Distance Fields in Indoor Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jang, Jaehoon, Lee, Inha, Kim, Minje, Joo, Kyungdon
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910381210861568
author Jang, Jaehoon
Lee, Inha
Kim, Minje
Joo, Kyungdon
author_facet Jang, Jaehoon
Lee, Inha
Kim, Minje
Joo, Kyungdon
contents Indoor scenes we are living in are visually homogenous or textureless, while they inherently have structural forms and provide enough structural priors for 3D scene reconstruction. Motivated by this fact, we propose a structure-aware online signed distance fields (SDF) reconstruction framework in indoor scenes, especially under the Atlanta world (AW) assumption. Thus, we dub this incremental SDF reconstruction for AW as AiSDF. Within the online framework, we infer the underlying Atlanta structure of a given scene and then estimate planar surfel regions supporting the Atlanta structure. This Atlanta-aware surfel representation provides an explicit planar map for a given scene. In addition, based on these Atlanta planar surfel regions, we adaptively sample and constrain the structural regularity in the SDF reconstruction, which enables us to improve the reconstruction quality by maintaining a high-level structure while enhancing the details of a given scene. We evaluate the proposed AiSDF on the ScanNet and ReplicaCAD datasets, where we demonstrate that the proposed framework is capable of reconstructing fine details of objects implicitly, as well as structures explicitly in room-scale scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2403_01861
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AiSDF: Structure-aware Neural Signed Distance Fields in Indoor Scenes
Jang, Jaehoon
Lee, Inha
Kim, Minje
Joo, Kyungdon
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Indoor scenes we are living in are visually homogenous or textureless, while they inherently have structural forms and provide enough structural priors for 3D scene reconstruction. Motivated by this fact, we propose a structure-aware online signed distance fields (SDF) reconstruction framework in indoor scenes, especially under the Atlanta world (AW) assumption. Thus, we dub this incremental SDF reconstruction for AW as AiSDF. Within the online framework, we infer the underlying Atlanta structure of a given scene and then estimate planar surfel regions supporting the Atlanta structure. This Atlanta-aware surfel representation provides an explicit planar map for a given scene. In addition, based on these Atlanta planar surfel regions, we adaptively sample and constrain the structural regularity in the SDF reconstruction, which enables us to improve the reconstruction quality by maintaining a high-level structure while enhancing the details of a given scene. We evaluate the proposed AiSDF on the ScanNet and ReplicaCAD datasets, where we demonstrate that the proposed framework is capable of reconstructing fine details of objects implicitly, as well as structures explicitly in room-scale scenes.
title AiSDF: Structure-aware Neural Signed Distance Fields in Indoor Scenes
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.01861