Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Plenoxels: Radiance Fields without Neural Networks

About

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.

Alex Yu, Sara Fridovich-Keil, Matthew Tancik, Qinhong Chen, Benjamin Recht, Angjoo Kanazawa• 2021

Related benchmarks

TaskDatasetResultRank
Novel View SynthesisTanks&Temples (test)
PSNR27.43
257
Novel View SynthesisMip-NeRF 360 (test)
PSNR23.62
184
Novel View SynthesisMip-NeRF 360
PSNR23.62
143
Novel View SynthesisMip-NeRF360
PSNR23.08
138
Novel View SynthesisLLFF
PSNR26.29
130
Novel View SynthesisScanNet
PSNR22.35
130
Novel View SynthesisNeRF Synthetic
PSNR31.76
110
Novel View SynthesisLLFF (test)
PSNR26.29
91
Novel View SynthesisDeep Blending (test)
PSNR23.06
72
3D ReconstructionMip-NeRF 360
PSNR23.08
66
Showing 10 of 46 rows

Other info

Follow for update