NerfBaselines: Consistent and Reproducible Evaluation of Novel View Synthesis Methods
This addresses a critical issue for researchers in computer vision and graphics by enabling reliable comparisons of methods like NeRFs and 3DGS, though it is incremental as it builds on existing evaluation practices.
The paper tackles the problem of inconsistent and non-reproducible evaluation in novel view synthesis, showing that small differences in protocols can artificially boost performance, and proposes NerfBaselines, a framework that provides consistent benchmarking tools and ensures reproducibility, validated by reproducing original paper numbers.
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.