ScanNeRF: a Scalable Benchmark for Neural Radiance Fields

TL;DR

ScanNeRF introduces a scalable, cost-effective benchmark platform and dataset for evaluating Neural Radiance Fields, enabling rapid scanning and comprehensive performance assessment of NeRF methods.

Contribution

We develop the first real benchmark for NeRFs, including a low-cost scanning platform and a diverse dataset for systematic evaluation.

Findings

Evaluated three state-of-the-art NeRF variants on ScanNeRF.

Demonstrated the platform's ability to quickly scan objects with minimal hardware.

Provided insights into the strengths and weaknesses of current NeRF methods.

Abstract

In this paper, we propose the first-ever real benchmark thought for evaluating Neural Radiance Fields (NeRFs) and, in general, Neural Rendering (NR) frameworks. We design and implement an effective pipeline for scanning real objects in quantity and effortlessly. Our scan station is built with less than 500$ hardware budget and can collect roughly 4000 images of a scanned object in just 5 minutes. Such a platform is used to build ScanNeRF, a dataset characterized by several train/val/test splits aimed at benchmarking the performance of modern NeRF methods under different conditions. Accordingly, we evaluate three cutting-edge NeRF variants on it to highlight their strengths and weaknesses. The dataset is available on our project page, together with an online benchmark to foster the development of better and better NeRFs.