Neural Fields for Scalable Scene Reconstruction

DC I/O 2021 Keynote by JAMES TOMPKIN. https://doi.org/10.47330/DCIO.2022.AXBL8798

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

Video Recording.

Conference Paper

Conference Paper.

Keywords

AI, Architect, Creativity, Displacement, Intelligence, Human, Machine, Software, Utilitarianism, Value

Reference

DOI: https://doi.org/10.47330/DCIO.2022.AXBL8798

Bibliography

• 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.