Plenoxels: Radiance Fields without Neural Networks — mentioned by crubier

Sat, 26 Mar 2022 13:05:20 GMT

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

Paper and discussion history. A mention is not an endorsement.

Plenoxels: Radiance Fields without Neural Networks — mentioned by sanxiyn

Mon, 27 Dec 2021 03:07:53 GMT

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 found you can get NeRF quality without any neural network at all and as a result 100x faster.

Paper and discussion history. A mention is not an endorsement.

Plenoxels: Radiance Fields without Neural Networks · HackerPapers discussions

Plenoxels: Radiance Fields without Neural Networks — mentioned by crubier

Plenoxels: Radiance Fields without Neural Networks — mentioned by sanxiyn