Difference between revisions of "Neural Fields for Scalable Scene Reconstruction"

From Design Computation
Jump to: navigation, search
(→‎Abstract)
(→‎Keywords)
 
(36 intermediate revisions by 2 users not shown)
Line 1: Line 1:
−
[[File:DCIO2021-Logo.png|right|250px|link=DC_I/O_2022]]
+
[[File:DCIO2022-Logo.png|right|200px|link=DC_I/O_2022]]
 
[[Category:DCIO]]
 
[[Category:DCIO]]
−
[[Category:DCIO2021]]
+
[[Category:DCIO2022]]
 
[[Category:DCIO Proceedings]]
 
[[Category:DCIO Proceedings]]
 
[[Category:Conferences]]
 
[[Category:Conferences]]
 
[[Category:Book]]
 
[[Category:Book]]
−
[[DC I/O 2021]] Keynote by [https://jamestompkin.com// JAMES TOMPKIN]. https://doi.org/10.47330/DCIO.2022.AXBL8798
+
[[DC I/O 2022]] Keynote by [https://jamestompkin.com// James Tompkin]. https://doi.org/10.47330/DCIO.2022.AXBL8798 | [[File:VideoRecord-Icon.png |Left|22px|link=https://youtu.be/tmuQJCVKTuI]] | [[File:Paper-Icon.png |Left|30px|link=https://www.dropbox.com/]] | [[File:Poster-Icon.png |Left|30px|link=https://www.dropbox.com/]] | [[File:Slides-Icon.png |Left|30px|link=https://www.dropbox.com/]]
  
−
[[File:DCIO2021 F-Berar.png|center|800px]]
 
  
−
=Abstract=
 
−
Neural fields are a new (and old!) approach to solving problems over spacetime via first-order optimization of a neural network. Over the past three years, combining neural fields with classic computer graphics approaches have allowed us to make significant advances in solving computer vision problems like scene reconstruction. I will present recent work that can reconstruct indoor scenes for photorealistic interactive exploration using new scalable hybrid neural field representations. This has applications where any real-world place needs to be digitized, especially for visualization purposes.
 
  
−
=Presentation=
+
[[File:DCIO2022 S1 1 J-Tompkin.png|center|800px]]
−
[[File:YouTube.png |Left|50px|link=https://www.youtube.com/watch?v=T_wkB680Hrw]] [https://www.youtube.com/watch?v=T_wkB680Hrw Video Recording].
+
 
  
−
=Conference Paper=
+
=Abstract=
−
[[File:PDF-Icon.png |Left|50px|link=https://www.dropbox.com/s/99ql59hn2ngyb11/DCIO2021_S3-3_F.Berar.pdf?dl=0]] [https://www.dropbox.com/s/99ql59hn2ngyb11/DCIO2021_S3-3_F.Berar.pdf?dl=0 Conference Paper].
+
Neural fields are a new (and old!) approach to solving problems over spacetime via first-order optimization of a neural network. Over the past three years, combining neural fields with classic computer graphics approaches have allowed us to make significant advances in solving computer vision problems like scene reconstruction. I will present recent work that can reconstruct indoor scenes for photorealistic interactive exploration using new scalable hybrid neural field representations. This has applications where any real-world place needs to be digitized, especially for visualization purposes.
  
 
=Keywords=
 
=Keywords=
−
[[AI]], [[Architect]], [[Creativity]], [[Displacement]], [[Intelligence]], [[Human]], [[Machine]], [[Software]], [[Utilitarianism]], [[Value]]
+
[[AI]], [[Architect]], [[Neural Fields]].
−
 
 
−
=Reference=
 
−
DOI: https://doi.org/10.47330/DCIO.2022.AXBL8798
 
  
 
=Bibliography=
 
=Bibliography=
 
*Anderson, T.T., 2011. Complicating Heidegger and the Truth of Architecture. The Journal of Aesthetics and Art Criticism 69, 69–79.
 
*Anderson, T.T., 2011. Complicating Heidegger and the Truth of Architecture. The Journal of Aesthetics and Art Criticism 69, 69–79.
−
*Arendt, H., 1998. The Human Condition, 2nd ed. The University of Chicago Press, Chicago.
 
−
*Beavers, A.F., 2002. Phenomenology and Artificial Intelligence. Metaphilosophy 33, 70–82.
 
−
*Berkowitz, R., 2018. The Singularity and the Human Condition. Philosophy Today; Charlottesville 62, 337–355.
 

Latest revision as of 12:45, 18 April 2023

DCIO2022-Logo.png
DC I/O 2022 Keynote by James Tompkin. https://doi.org/10.47330/DCIO.2022.AXBL8798 | Left | Left | Left | Left


DCIO2022 S1 1 J-Tompkin.png


Abstract

Neural fields are a new (and old!) approach to solving problems over spacetime via first-order optimization of a neural network. Over the past three years, combining neural fields with classic computer graphics approaches have allowed us to make significant advances in solving computer vision problems like scene reconstruction. I will present recent work that can reconstruct indoor scenes for photorealistic interactive exploration using new scalable hybrid neural field representations. This has applications where any real-world place needs to be digitized, especially for visualization purposes.

Keywords

AI, Architect, Neural Fields.

Bibliography

  • Anderson, T.T., 2011. Complicating Heidegger and the Truth of Architecture. The Journal of Aesthetics and Art Criticism 69, 69–79.
Retrieved from "http://wiki.designcomputation.org/home/index.php?title=Neural_Fields_for_Scalable_Scene_Reconstruction&oldid=27405"