DeepAI
Log In Sign Up

DeRF: Decomposed Radiance Fields

11/25/2020
by   Daniel Rebain, et al.
8

With the advent of Neural Radiance Fields (NeRF), neural networks can now render novel views of a 3D scene with quality that fools the human eye. Yet, generating these images is very computationally intensive, limiting their applicability in practical scenarios. In this paper, we propose a technique based on spatial decomposition capable of mitigating this issue. Our key observation is that there are diminishing returns in employing larger (deeper and/or wider) networks. Hence, we propose to spatially decompose a scene and dedicate smaller networks for each decomposed part. When working together, these networks can render the whole scene. This allows us near-constant inference time regardless of the number of decomposed parts. Moreover, we show that a Voronoi spatial decomposition is preferable for this purpose, as it is provably compatible with the Painter's Algorithm for efficient and GPU-friendly rendering. Our experiments show that for real-world scenes, our method provides up to 3x more efficient inference than NeRF (with the same rendering quality), or an improvement of up to 1.0 dB in PSNR (for the same inference cost).

READ FULL TEXT

page 1

page 3

page 4

page 7

page 8

page 14

11/21/2022

Tensor4D : Efficient Neural 4D Decomposition for High-fidelity Dynamic Reconstruction and Rendering

We present Tensor4D, an efficient yet effective approach to dynamic scen...
12/07/2020

NeRD: Neural Reflectance Decomposition from Image Collections

Decomposing a scene into its shape, reflectance, and illumination is a c...
10/28/2022

NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields

Visually exploring in a real-world 4D spatiotemporal space freely in VR ...
06/30/2013

Progressive Blue Surfels

In this paper we describe a new technique to generate and use surfels fo...
11/22/2022

Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition

While dynamic Neural Radiance Fields (NeRF) have shown success in high-f...
06/02/2022

EfficientNeRF: Efficient Neural Radiance Fields

Neural Radiance Fields (NeRF) has been wildly applied to various tasks f...
04/17/2019

Rendering of Complex Heterogenous Scenes using Progressive Blue Surfels

We present a technique for rendering highly complex 3D scenes in real-ti...

Code Repositories