Plenoxels: Radiance Fields without Neural Networks

12/09/2021

∙

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.

READ FULL TEXT

Plenoxels: Radiance Fields without Neural Networks

Baking Neural Radiance Fields for Real-Time View Synthesis

Differentiable Point-Based Radiance Fields for Efficient View Synthesis

NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks

From data to functa: Your data point is a function and you should treat it like one

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

Automated Design using Neural Networks and Gradient Descent

Balanced Spherical Grid for Egocentric View Synthesis

Plenoxels: Radiance Fields without Neural Networks

Related Research

Baking Neural Radiance Fields for Real-Time View Synthesis

Differentiable Point-Based Radiance Fields for Efficient View Synthesis

NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks

From data to functa: Your data point is a function and you should treat it like one

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

Automated Design using Neural Networks and Gradient Descent

Balanced Spherical Grid for Egocentric View Synthesis