Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations
Abstract
Recent years have witnessed substantial progress on monocular depth estimation, particularly as measured by the success of large models on standard benchmarks. However, performance on standard benchmarks does not offer a complete assessment, because most evaluate accuracy but not robustness. In this work, we introduce PDE (Procedural Depth Evaluation), a new benchmark which enables systematic evaluation of robustness to changes in 3D scene content. PDE uses procedural generation to create 3D scenes that test robustness to various controlled perturbations, including object, camera, material and lighting changes. Our analysis yields interesting findings on what perturbations are challenging for state-of-the-art depth models, which we hope will inform further research. Code and data are available at https://github.com/princeton-vl/proc-depth-eval.
Cite
Text
Nugent et al. "Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations." Advances in Neural Information Processing Systems, 2025.Markdown
[Nugent et al. "Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations." Advances in Neural Information Processing Systems, 2025.](https://mlanthology.org/neurips/2025/nugent2025neurips-evaluating/)BibTeX
@inproceedings{nugent2025neurips-evaluating,
title = {{Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations}},
author = {Nugent, John and Wu, Siyang and Ma, Zeyu and Han, Beining and Parakh, Meenal and Joshi, Abhishek and Mei, Lingjie and Raistrick, Alexander and Li, Xinyuan and Deng, Jia},
booktitle = {Advances in Neural Information Processing Systems},
year = {2025},
url = {https://mlanthology.org/neurips/2025/nugent2025neurips-evaluating/}
}