Depth-Relative Self Attention for Monocular Depth Estimation

• URL: http://arxiv.org/abs/2304.12849v1
• Date: Tue, 25 Apr 2023 14:20:31 GMT
• Title: Depth-Relative Self Attention for Monocular Depth Estimation
• Authors: Kyuhong Shim, Jiyoung Kim, Gusang Lee, Byonghyo Shim
• Abstract summary: deep neural networks rely on various visual hints such as size, shade, and texture extracted from RGB information. We propose a novel depth estimation model named RElative Depth Transformer (RED-T) that uses relative depth as guidance in self-attention. We show that the proposed model achieves competitive results in monocular depth estimation benchmarks and is less biased to RGB information.
• Score: 23.174459018407003
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Monocular depth estimation is very challenging because clues to the exact depth are incomplete in a single RGB image. To overcome the limitation, deep neural networks rely on various visual hints such as size, shade, and texture extracted from RGB information. However, we observe that if such hints are overly exploited, the network can be biased on RGB information without considering the comprehensive view. We propose a novel depth estimation model named RElative Depth Transformer (RED-T) that uses relative depth as guidance in self-attention. Specifically, the model assigns high attention weights to pixels of close depth and low attention weights to pixels of distant depth. As a result, the features of similar depth can become more likely to each other and thus less prone to misused visual hints. We show that the proposed model achieves competitive results in monocular depth estimation benchmarks and is less biased to RGB information. In addition, we propose a novel monocular depth estimation benchmark that limits the observable depth range during training in order to evaluate the robustness of the model for unseen depths.

Related papers

• Self-Supervised Learning based Depth Estimation from Monocular Images [0.0]
  The goal of Monocular Depth Estimation is to predict the depth map, given a 2D monocular RGB image as input. We plan to do intrinsic camera parameters during training and apply weather augmentations to further generalize our model.
  arXiv  Detail & Related papers  (2023-04-14T07:14:08Z)
• RGB-D Grasp Detection via Depth Guided Learning with Cross-modal Attention [14.790193023912973]
  This paper proposes a novel learning based approach to RGB-D grasp detection, namely Depth Guided Cross-modal Attention Network (DGCAN) To better leverage the geometry information recorded in the depth channel, a complete 6-dimensional rectangle representation is adopted with the grasp depth dedicatedly considered. The prediction of the extra grasp depth substantially strengthens feature learning, thereby leading to more accurate results.
  arXiv  Detail & Related papers  (2023-02-28T02:41:27Z)
• Monocular Depth Estimation Using Cues Inspired by Biological Vision Systems [22.539300644593936]
  Monocular depth estimation (MDE) aims to transform an RGB image of a scene into a pixelwise depth map from the same camera view. Part of the MDE task is to learn which visual cues in the image can be used for depth estimation, and how. We demonstrate that explicitly injecting visual cue information into the model is beneficial for depth estimation.
  arXiv  Detail & Related papers  (2022-04-21T19:42:36Z)
• RGB-Depth Fusion GAN for Indoor Depth Completion [29.938869342958125]
  In this paper, we design a novel two-branch end-to-end fusion network, which takes a pair of RGB and incomplete depth images as input to predict a dense and completed depth map. In one branch, we propose an RGB-depth fusion GAN to transfer the RGB image to the fine-grained textured depth map. In the other branch, we adopt adaptive fusion modules named W-AdaIN to propagate the features across the two branches.
  arXiv  Detail & Related papers  (2022-03-21T10:26:38Z)
• Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction [91.43066633305662]
  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. 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.
  arXiv  Detail & Related papers  (2022-03-09T17:20:18Z)
• Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data [73.9872931307401]
  We propose a novel weakly-supervised framework to train a monocular depth estimation network. The proposed framework is composed of a sharing weight monocular depth estimation network and a depth reconstruction network for distillation. Experimental results demonstrate that our method achieves superior performance than unsupervised and semi-supervised learning based schemes.
  arXiv  Detail & Related papers  (2021-09-23T18:04:12Z)
• Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion [56.85837052421469]
  Estimating scene geometry from data obtained with cost-effective sensors is key for robots and self-driving cars. In this paper, we study the problem of predicting dense depth from a single RGB image with optional sparse measurements from low-cost active depth sensors. We introduce Sparse Networks (SANs), a new module enabling monodepth networks to perform both the tasks of depth prediction and completion.
  arXiv  Detail & Related papers  (2021-03-30T21:22:26Z)
• Efficient Depth Completion Using Learned Bases [94.0808155168311]
  We propose a new global geometry constraint for depth completion. By assuming depth maps often lay on low dimensional subspaces, a dense depth map can be approximated by a weighted sum of full-resolution principal depth bases.
  arXiv  Detail & Related papers  (2020-12-02T11:57:37Z)
• Accurate RGB-D Salient Object Detection via Collaborative Learning [101.82654054191443]
  RGB-D saliency detection shows impressive ability on some challenge scenarios. We propose a novel collaborative learning framework where edge, depth and saliency are leveraged in a more efficient way.
  arXiv  Detail & Related papers  (2020-07-23T04:33:36Z)
• Single Image Depth Estimation Trained via Depth from Defocus Cues [105.67073923825842]
  Estimating depth from a single RGB image is a fundamental task in computer vision. In this work, we rely, instead of different views, on depth from focus cues. We present results that are on par with supervised methods on KITTI and Make3D datasets and outperform unsupervised learning approaches.
  arXiv  Detail & Related papers  (2020-01-14T20:22:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.