DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Rendering

11/19/2021
by   Liwen Wu, et al.
10

DIVeR builds on the key ideas of NeRF and its variants – density models and volume rendering – to learn 3D object models that can be rendered realistically from small numbers of images. In contrast to all previous NeRF methods, DIVeR uses deterministic rather than stochastic estimates of the volume rendering integral. DIVeR's representation is a voxel based field of features. To compute the volume rendering integral, a ray is broken into intervals, one per voxel; components of the volume rendering integral are estimated from the features for each interval using an MLP, and the components are aggregated. As a result, DIVeR can render thin translucent structures that are missed by other integrators. Furthermore, DIVeR's representation has semantics that is relatively exposed compared to other such methods – moving feature vectors around in the voxel space results in natural edits. Extensive qualitative and quantitative comparisons to current state-of-the-art methods show that DIVeR produces models that (1) render at or above state-of-the-art quality, (2) are very small without being baked, (3) render very fast without being baked, and (4) can be edited in natural ways.

READ FULL TEXT

page 1

page 3

page 6

page 7

page 8

research
09/28/2021

Common Artifacts in Volume Rendering

Direct Volume Rendering is a popular and powerful visualization method f...
research
04/20/2023

Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering

The rendering scheme in neural radiance field (NeRF) is effective in ren...
research
12/11/2018

Antara: An Interactive 3D Volume Rendering and Visualization Framework

The goal of 3D visualization is to provide the user with an intuitive in...
research
07/22/2020

Neural Sparse Voxel Fields

Photo-realistic free-viewpoint rendering of real-world scenes using clas...
research
07/27/2021

Differentiable Direct Volume Rendering

We present a differentiable volume rendering solution that provides diff...
research
12/03/2020

AutoInt: Automatic Integration for Fast Neural Volume Rendering

Numerical integration is a foundational technique in scientific computin...
research
02/24/2012

Efficient and Effective Volume Visualization with Enhanced Isosurface Rendering

Compared with full volume rendering, isosurface rendering has several we...

Please sign up or login with your details

Forgot password? Click here to reset