ScanNeRF: a Scalable Benchmark for Neural Radiance Fields
This provides a standardized benchmark for the NeRF community, enabling better evaluation and development of neural rendering methods, though it is incremental as it builds on existing NeRF frameworks.
The authors tackled the lack of a real benchmark for Neural Radiance Fields (NeRFs) by creating ScanNeRF, a scalable dataset built with a low-cost scanning pipeline that collects 4000 images in 5 minutes, and they evaluated three NeRF variants to highlight performance differences.
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.