IEBins: Iterative Elastic Bins for Monocular Depth Estimation
Monocular depth estimation (MDE) is a fundamental topic of geometric computer vision and a core technique for many downstream applications. Recently, several methods reframe the MDE as a classification-regression problem where a linear combination of probabilistic distribution and bin centers is used to predict depth. In this paper, we propose a novel concept of iterative elastic bins (IEBins) for the classification-regression-based MDE. The proposed IEBins aims to search for high-quality depth by progressively optimizing the search range, which involves multiple stages and each stage performs a finer-grained depth search in the target bin on top of its previous stage. To alleviate the possible error accumulation during the iterative process, we utilize a novel elastic target bin to replace the original target bin, the width of which is adjusted elastically based on the depth uncertainty. Furthermore, we develop a dedicated framework composed of a feature extractor and an iterative optimizer that has powerful temporal context modeling capabilities benefiting from the GRU-based architecture. Extensive experiments on the KITTI, NYU-Depth-v2 and SUN RGB-D datasets demonstrate that the proposed method surpasses prior state-of-the-art competitors. The source code is publicly available at https://github.com/ShuweiShao/IEBins.
PDF Abstract NeurIPS 2023 PDF NeurIPS 2023 AbstractResults from the Paper
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Monocular Depth Estimation | KITTI Eigen split | IEBins | absolute relative error | 0.050 | # 13 | |
RMSE | 2.011 | # 12 | ||||
Sq Rel | 0.142 | # 13 | ||||
RMSE log | 0.075 | # 12 | ||||
Delta < 1.25 | 0.978 | # 11 | ||||
Delta < 1.25^2 | 0.998 | # 1 | ||||
Delta < 1.25^3 | 0.999 | # 11 | ||||
Monocular Depth Estimation | NYU-Depth V2 | IEBins | RMSE | 0.314 | # 22 | |
absolute relative error | 0.087 | # 22 | ||||
Delta < 1.25 | 0.936 | # 22 | ||||
Delta < 1.25^2 | 0.992 | # 17 | ||||
Delta < 1.25^3 | 0.998 | # 18 | ||||
log 10 | 0.038 | # 23 |