HackerPapers

arXiv:2112.05131cs.CV

Plenoxels: Radiance Fields without Neural Networks

Alex Yu, Sara Fridovich-Keil, Matthew Tancik, Qinhong Chen, Benjamin Recht, Angjoo Kanazawa

Abstract

We introduce Plenoxels (plenoptic voxels), a system for photorealistic view synthesis. Plenoxels represent a scene as a sparse 3D grid with spherical harmonics. This representation can be optimized from calibrated images via gradient methods and regularization without any neural components. On standard, benchmark tasks, Plenoxels are optimized two orders of magnitude faster than Neural Radiance Fields with no loss in visual quality.

arXiv comments
For video and code, please see https://alexyu.net/plenoxels
Journal reference
DOI
Subjects
cs.CVComputer Vision and Pattern Recognition cs.GRGraphics

On Hacker News

Linked by 2 identifiable commenters in 2 comments across 2 threads, from Dec 2021 to Mar 2022.

Comments linking this paper, per year.

Discussed in comments2 threads

  1. Nvidia Research Turns 2D Photos into 3D Scenes 1 comment

    • You are right, this is why approaches like plenoxels are vastly faster than nerf. They combine the optimization approach of neural nets, but combine it with a simple and regular data representation of the scene. https://arxiv.org/pdf/2112.05131.pdf

      crubierView on HNParent context

  2. HyperNeRF 1 comment

    • Since neural networks are universal, we can often solve problems we don't know exactly how to solve with neural networks. NeRF is a great example. But once solved, we should try to reverse engineer the solution and optimize. https://arxiv.org/abs/2112.05131 did such work and…

      sanxiynView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.