{
  "id": "2203.04895",
  "version": "v1",
  "published": "2022-03-09T17:20:18.000Z",
  "updated": "2022-03-09T17:20:18.000Z",
  "title": "Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction",
  "authors": [
    "Xiaoqi Zhao",
    "Youwei Pang",
    "Lihe Zhang",
    "Huchuan Lu"
  ],
  "comment": "Manuscript Version",
  "categories": [
    "cs.CV"
  ],
  "abstract": "Benefiting from color independence, illumination invariance and location discrimination attributed by the depth map, it can provide important supplemental information for extracting salient objects in complex environments. However, high-quality depth sensors are expensive and can not be widely applied. While general depth sensors produce the noisy and sparse depth information, which brings the depth-based networks with irreversible interference. In this paper, we propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD). Specifically, we unify three complementary tasks: depth estimation, salient object detection and contour estimation. The multi-task mechanism promotes the model to learn the task-aware features from the auxiliary tasks. In this way, the depth information can be completed and purified. Moreover, we introduce a multi-modal filtered transformer (MFT) module, which equips with three modality-specific filters to generate the transformer-enhanced feature for each modality. The proposed model works in a depth-free style during the testing phase. Experiments show that it not only significantly surpasses the depth-based RGB-D SOD methods on multiple datasets, but also precisely predicts a high-quality depth map and salient contour at the same time. And, the resulted depth map can help existing RGB-D SOD methods obtain significant performance gain.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-03-09T17:20:18.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "depth estimation",
      "contour extraction",
      "depth map",
      "joint learning",
      "multi-modal filtered transformer"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}