File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Book Chapter: NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors

TitleNeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors
Authors
KeywordsAdaptive prior
Indoor reconstruction
Neural volume rendering
Issue Date10-Nov-2022
PublisherSpringer
Abstract

Reconstructing 3D indoor scenes from 2D images is an important task in many computer vision and graphics applications. A main challenge in this task is that large texture-less areas in typical indoor scenes make existing methods struggle to produce satisfactory reconstruction results. We propose a new method, named NeuRIS, for high-quality reconstruction of indoor scenes. The key idea of NeuRIS is to integrate estimated normal of indoor scenes as a prior in a neural rendering framework for reconstructing large texture-less shapes and, importantly, to do this in an adaptive manner to also enable the reconstruction of irregular shapes with fine details. Specifically, we evaluate the faithfulness of the normal priors on-the-fly by checking the multi-view consistency of reconstruction during the optimization process. Only the normal priors accepted as faithful will be utilized for 3D reconstruction, which typically happens in the regions of smooth shapes possibly with weak texture. However, for those regions with small objects or thin structures, for which the normal priors are usually unreliable, we will only rely on visual features of the input images, since such regions typically contain relatively rich visual features (e.g., shade changes and boundary contours). Extensive experiments show that NeuRIS significantly outperforms the state-of-the-art methods in terms of reconstruction quality. Our project page: https://jiepengwang.github.io/NeuRIS/.


Persistent Identifierhttp://hdl.handle.net/10722/337673
ISBN
ISSN
2023 SCImago Journal Rankings: 0.606
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorWang, Jiepeng-
dc.contributor.authorWang, Peng-
dc.contributor.authorLong, Xiaoxiao-
dc.contributor.authorTheobalt, Christian-
dc.contributor.authorKomura, Taku-
dc.contributor.authorLiu, Lingjie-
dc.contributor.authorWang, Wenping-
dc.date.accessioned2024-03-11T10:22:58Z-
dc.date.available2024-03-11T10:22:58Z-
dc.date.issued2022-11-10-
dc.identifier.isbn9783031198236-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/337673-
dc.description.abstract<p> Reconstructing 3D indoor scenes from 2D images is an important task in many computer vision and graphics applications. A main challenge in this task is that large texture-less areas in typical indoor scenes make existing methods struggle to produce satisfactory reconstruction results. We propose a new method, named <em>NeuRIS</em>, for high-quality reconstruction of indoor scenes. The key idea of <em>NeuRIS</em> is to integrate estimated normal of indoor scenes as a prior in a neural rendering framework for reconstructing large texture-less shapes and, importantly, to do this in an adaptive manner to also enable the reconstruction of irregular shapes with fine details. Specifically, we evaluate the faithfulness of the normal priors on-the-fly by checking the multi-view consistency of reconstruction during the optimization process. Only the normal priors accepted as faithful will be utilized for 3D reconstruction, which typically happens in the regions of smooth shapes possibly with weak texture. However, for those regions with small objects or thin structures, for which the normal priors are usually unreliable, we will only rely on visual features of the input images, since such regions typically contain relatively rich visual features (e.g., shade changes and boundary contours). Extensive experiments show that <em>NeuRIS</em> significantly outperforms the state-of-the-art methods in terms of reconstruction quality. Our project page: <a href="https://jiepengwang.github.io/NeuRIS/">https://jiepengwang.github.io/NeuRIS/.</a> <br></p>-
dc.languageeng-
dc.publisherSpringer-
dc.relation.ispartofComputer Vision – ECCV 2022-
dc.subjectAdaptive prior-
dc.subjectIndoor reconstruction-
dc.subjectNeural volume rendering-
dc.titleNeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors-
dc.typeBook_Chapter-
dc.identifier.doi10.1007/978-3-031-19824-3_9-
dc.identifier.scopuseid_2-s2.0-85144579299-
dc.identifier.volume13692 LNCS-
dc.identifier.spage139-
dc.identifier.epage155-
dc.identifier.eissn1611-3349-
dc.identifier.isiWOS:000903565400009-
dc.identifier.eisbn9783031198243-
dc.identifier.issnl0302-9743-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats