File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images

TitleNeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images
Authors
Keywordsmultiview reconstruction
neural rendering
neural representation
Issue Date26-Jul-2023
PublisherAssociation for Computing Machinery (ACM)
Citation
ACM Transactions on Graphics, 2023, v. 42, n. 4 How to Cite?
Abstract

We present a neural rendering-based method called NeRO for reconstructing the geometry and the BRDF of reflective objects from multiview images captured in an unknown environment. Multiview reconstruction of reflective objects is extremely challenging because specular reflections are view-dependent and thus violate the multiview consistency, which is the cornerstone for most multiview reconstruction methods. Recent neural rendering techniques can model the interaction between environment lights and the object surfaces to fit the view-dependent reflections, thus making it possible to reconstruct reflective objects from multiview images. However, accurately modeling environment lights in the neural rendering is intractable, especially when the geometry is unknown. Most existing neural rendering methods, which can model environment lights, only consider direct lights and rely on object masks to reconstruct objects with weak specular reflections. Therefore, these methods fail to reconstruct reflective objects, especially when the object mask is not available and the object is illuminated by indirect lights. We propose a two-step approach to tackle this problem. First, by applying the split-sum approximation and the integrated directional encoding to approximate the shading effects of both direct and indirect lights, we are able to accurately reconstruct the geometry of reflective objects without any object masks. Then, with the object geometry fixed, we use more accurate sampling to recover the environment lights and the BRDF of the object. Extensive experiments demonstrate that our method is capable of accurately reconstructing the geometry and the BRDF of reflective objects from only posed RGB images without knowing the environment lights and the object masks. Codes and datasets are available at https://github.com/liuyuan-pal/NeRO.


Persistent Identifierhttp://hdl.handle.net/10722/331625
ISSN
2023 Impact Factor: 7.8
2023 SCImago Journal Rankings: 7.766
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLiu, Yuan-
dc.contributor.authorWang, Peng-
dc.contributor.authorLin, Cheng-
dc.contributor.authorLong, Xiaoxiao-
dc.contributor.authorWang, Jiepeng-
dc.contributor.authorLiu, Lingjie-
dc.contributor.authorKomura, Taku-
dc.contributor.authorWang, Wenping-
dc.date.accessioned2023-09-21T06:57:28Z-
dc.date.available2023-09-21T06:57:28Z-
dc.date.issued2023-07-26-
dc.identifier.citationACM Transactions on Graphics, 2023, v. 42, n. 4-
dc.identifier.issn0730-0301-
dc.identifier.urihttp://hdl.handle.net/10722/331625-
dc.description.abstract<p> We present a neural rendering-based method called NeRO for reconstructing the geometry and the BRDF of reflective objects from multiview images captured in an unknown environment. Multiview reconstruction of reflective objects is extremely challenging because specular reflections are view-dependent and thus violate the multiview consistency, which is the cornerstone for most multiview reconstruction methods. Recent neural rendering techniques can model the interaction between environment lights and the object surfaces to fit the view-dependent reflections, thus making it possible to reconstruct reflective objects from multiview images. However, accurately modeling environment lights in the neural rendering is intractable, especially when the geometry is unknown. Most existing neural rendering methods, which can model environment lights, only consider direct lights and rely on object masks to reconstruct objects with weak specular reflections. Therefore, these methods fail to reconstruct reflective objects, especially when the object mask is not available and the object is illuminated by indirect lights. We propose a two-step approach to tackle this problem. First, by applying the split-sum approximation and the integrated directional encoding to approximate the shading effects of both direct and indirect lights, we are able to accurately reconstruct the geometry of reflective objects without any object masks. Then, with the object geometry fixed, we use more accurate sampling to recover the environment lights and the BRDF of the object. Extensive experiments demonstrate that our method is capable of accurately reconstructing the geometry and the BRDF of reflective objects from only posed RGB images without knowing the environment lights and the object masks. Codes and datasets are available at https://github.com/liuyuan-pal/NeRO. <br></p>-
dc.languageeng-
dc.publisherAssociation for Computing Machinery (ACM)-
dc.relation.ispartofACM Transactions on Graphics-
dc.subjectmultiview reconstruction-
dc.subjectneural rendering-
dc.subjectneural representation-
dc.titleNeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images-
dc.typeArticle-
dc.identifier.doi10.1145/3592134-
dc.identifier.scopuseid_2-s2.0-85166632595-
dc.identifier.volume42-
dc.identifier.issue4-
dc.identifier.eissn1557-7368-
dc.identifier.isiWOS:001044671300080-
dc.identifier.issnl0730-0301-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats