NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods

TL;DR

NerfBaselines offers a standardized, reproducible evaluation framework for novel view synthesis methods like NeRFs and 3DGS, addressing inconsistencies in protocols and facilitating fair comparisons across different approaches.

Contribution

It introduces a comprehensive benchmarking tool that ensures consistent evaluation, reproducibility, and easier adoption of various view synthesis methods, enhancing research comparability.

Findings

Evaluation protocol differences can artificially inflate performance metrics.

Reproduced original results confirming the framework's accuracy.

Web platform enables easy comparison of methods on standard benchmarks.

Abstract

Novel view synthesis is an important problem with many applications, including AR/VR, gaming, and robotic simulations. With the recent rapid development of Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) methods, it is becoming difficult to keep track of the current state of the art (SoTA) due to methods using different evaluation protocols, codebases being difficult to install and use, and methods not generalizing well to novel 3D scenes. In our experiments, we show that even tiny differences in the evaluation protocols of various methods can artificially boost the performance of these methods. This raises questions about the validity of quantitative comparisons performed in the literature. To address these questions, we propose NerfBaselines, an evaluation framework which provides consistent benchmarking tools, ensures reproducibility, and simplifies the installation and use of various methods. We validate our implementation experimentally by reproducing the numbers reported in the original papers. For improved accessibility, we release a web platform that compares commonly used methods on standard benchmarks. We strongly believe NerfBaselines is a valuable contribution to the community as it ensures that quantitative results are comparable and thus truly measure progress in the field of novel view synthesis.