Adaptive Voronoi NeRFs

03/28/2023
by   Tim Elsner, et al.
0

Neural Radiance Fields (NeRFs) learn to represent a 3D scene from just a set of registered images. Increasing sizes of a scene demands more complex functions, typically represented by neural networks, to capture all details. Training and inference then involves querying the neural network millions of times per image, which becomes impractically slow. Since such complex functions can be replaced by multiple simpler functions to improve speed, we show that a hierarchy of Voronoi diagrams is a suitable choice to partition the scene. By equipping each Voronoi cell with its own NeRF, our approach is able to quickly learn a scene representation. We propose an intuitive partitioning of the space that increases quality gains during training by distributing information evenly among the networks and avoids artifacts through a top-down adaptive refinement. Our framework is agnostic to the underlying NeRF method and easy to implement, which allows it to be applied to various NeRF variants for improved learning and rendering speeds.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 6

research
03/24/2021

Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields

The rendering procedure used by neural radiance fields (NeRF) samples a ...
research
03/25/2021

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

NeRF synthesizes novel views of a scene with unprecedented quality by fi...
research
06/02/2022

EfficientNeRF: Efficient Neural Radiance Fields

Neural Radiance Fields (NeRF) has been wildly applied to various tasks f...
research
06/13/2020

Equivariant Neural Rendering

We propose a framework for learning neural scene representations directl...
research
10/23/2022

Compressing Explicit Voxel Grid Representations: fast NeRFs become also small

NeRFs have revolutionized the world of per-scene radiance field reconstr...
research
05/07/2023

HashCC: Lightweight Method to Improve the Quality of the Camera-less NeRF Scene Generation

Neural Radiance Fields has become a prominent method of scene generation...
research
07/28/2023

Dynamic PlenOctree for Adaptive Sampling Refinement in Explicit NeRF

The explicit neural radiance field (NeRF) has gained considerable intere...

Please sign up or login with your details

Forgot password? Click here to reset