TermiNeRF: Ray Termination Prediction for Efficient Neural Rendering

TL;DR

TermiNeRF introduces a novel method that predicts ray termination points to significantly accelerate neural volume rendering, enabling faster training and rendering without sacrificing generality.

Contribution

It proposes a learned ray termination prediction model that speeds up neural rendering and can be trained end-to-end on general volumetric scenes.

Findings

Achieves an order of magnitude faster rendering.

Works with general volume data.

Supports end-to-end training.

Abstract

Volume rendering using neural fields has shown great promise in capturing and synthesizing novel views of 3D scenes. However, this type of approach requires querying the volume network at multiple points along each viewing ray in order to render an image, resulting in very slow rendering times. In this paper, we present a method that overcomes this limitation by learning a direct mapping from camera rays to locations along the ray that are most likely to influence the pixel's final appearance. Using this approach we are able to render, train and fine-tune a volumetrically-rendered neural field model an order of magnitude faster than standard approaches. Unlike existing methods, our approach works with general volumes and can be trained end-to-end.