{
  "id": "2309.14137",
  "version": "v1",
  "published": "2023-09-25T13:48:39.000Z",
  "updated": "2023-09-25T13:48:39.000Z",
  "title": "IEBins: Iterative Elastic Bins for Monocular Depth Estimation",
  "authors": [
    "Shuwei Shao",
    "Zhongcai Pei",
    "Xingming Wu",
    "Zhong Liu",
    "Weihai Chen",
    "Zhengguo Li"
  ],
  "comment": "Accepted by NeurIPS 2023",
  "categories": [
    "cs.CV"
  ],
  "abstract": "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-09-25T13:48:39.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "monocular depth estimation",
      "iterative elastic bins",
      "temporal context modeling capabilities",
      "target bin",
      "context modeling capabilities benefiting"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}