Towards Scale-Aware Full Surround Monodepth with Transformers

• URL: http://arxiv.org/abs/2407.10406v1
• Date: Mon, 15 Jul 2024 02:54:46 GMT
• Title: Towards Scale-Aware Full Surround Monodepth with Transformers
• Authors: Yuchen Yang, Xinyi Wang, Dong Li, Lu Tian, Ashish Sirasao, Xun Yang,
• Abstract summary: Full surround monodepth (FSM) methods can learn from multiple camera views simultaneously to predict the scale-aware depth. In this work, we focus on enhancing the scale-awareness of FSM methods for depth estimation.
• Score: 46.100897032607335
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Full surround monodepth (FSM) methods can learn from multiple camera views simultaneously in a self-supervised manner to predict the scale-aware depth, which is more practical for real-world applications in contrast to scale-ambiguous depth from a standalone monocular camera. In this work, we focus on enhancing the scale-awareness of FSM methods for depth estimation. To this end, we propose to improve FSM from two perspectives: depth network structure optimization and training pipeline optimization. First, we construct a transformer-based depth network with neighbor-enhanced cross-view attention (NCA). The cross-attention modules can better aggregate the cross-view context in both global and neighboring views. Second, we formulate a transformer-based feature matching scheme with progressive training to improve the structure-from-motion (SfM) pipeline. That allows us to learn scale-awareness with sufficient matches and further facilitate network convergence by removing mismatches based on SfM loss. Experiments demonstrate that the resulting Scale-aware full surround monodepth (SA-FSM) method largely improves the scale-aware depth predictions without median-scaling at the test time, and performs favorably against the state-of-the-art FSM methods, e.g., surpassing SurroundDepth by 3.8% in terms of accuracy at delta<1.25 on the DDAD benchmark.

Related papers

• Self-supervised Monocular Depth Estimation with Large Kernel Attention [30.44895226042849]
  We propose a self-supervised monocular depth estimation network to get finer details. Specifically, we propose a decoder based on large kernel attention, which can model long-distance dependencies. Our method achieves competitive results on the KITTI dataset.
  arXiv  Detail & Related papers  (2024-09-26T14:44:41Z)
• ARAI-MVSNet: A multi-view stereo depth estimation network with adaptive depth range and depth interval [19.28042366225802]
  Multi-View Stereo(MVS) is a fundamental problem in geometric computer vision. We present a novel multi-stage coarse-to-fine framework to achieve adaptive all-pixel depth range and depth interval. Our model achieves state-of-the-art performance and yields competitive generalization ability.
  arXiv  Detail & Related papers  (2023-08-17T14:52:11Z)
• DeepMLE: A Robust Deep Maximum Likelihood Estimator for Two-view Structure from Motion [9.294501649791016]
  Two-view structure from motion (SfM) is the cornerstone of 3D reconstruction and visual SLAM (vSLAM) We formulate the two-view SfM problem as a maximum likelihood estimation (MLE) and solve it with the proposed framework, denoted as DeepMLE. Our method significantly outperforms the state-of-the-art end-to-end two-view SfM approaches in accuracy and generalization capability.
  arXiv  Detail & Related papers  (2022-10-11T15:07:25Z)
• Improving Monocular Visual Odometry Using Learned Depth [84.05081552443693]
  We propose a framework to exploit monocular depth estimation for improving visual odometry (VO) The core of our framework is a monocular depth estimation module with a strong generalization capability for diverse scenes. Compared with current learning-based VO methods, our method demonstrates a stronger generalization ability to diverse scenes.
  arXiv  Detail & Related papers  (2022-04-04T06:26:46Z)
• VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction [71.83308989022635]
  In this paper, we advocate that replicating the traditional two stages framework with deep neural networks improves both the interpretability and the accuracy of the results. Our network operates in two steps: 1) the local computation of the local depth maps with a deep MVS technique, and, 2) the depth maps and images' features fusion to build a single TSDF volume. In order to improve the matching performance between images acquired from very different viewpoints, we introduce a rotation-invariant 3D convolution kernel called PosedConv.
  arXiv  Detail & Related papers  (2021-08-19T11:33:58Z)
• Deep Two-View Structure-from-Motion Revisited [83.93809929963969]
  Two-view structure-from-motion (SfM) is the cornerstone of 3D reconstruction and visual SLAM. We propose to revisit the problem of deep two-view SfM by leveraging the well-posedness of the classic pipeline. Our method consists of 1) an optical flow estimation network that predicts dense correspondences between two frames; 2) a normalized pose estimation module that computes relative camera poses from the 2D optical flow correspondences, and 3) a scale-invariant depth estimation network that leverages epipolar geometry to reduce the search space, refine the dense correspondences, and estimate relative depth maps.
  arXiv  Detail & Related papers  (2021-04-01T15:31:20Z)
• OmniSLAM: Omnidirectional Localization and Dense Mapping for Wide-baseline Multi-camera Systems [88.41004332322788]
  We present an omnidirectional localization and dense mapping system for a wide-baseline multiview stereo setup with ultra-wide field-of-view (FOV) fisheye cameras. For more practical and accurate reconstruction, we first introduce improved and light-weighted deep neural networks for the omnidirectional depth estimation. We integrate our omnidirectional depth estimates into the visual odometry (VO) and add a loop closing module for global consistency.
  arXiv  Detail & Related papers  (2020-03-18T05:52:10Z)
• Video Depth Estimation by Fusing Flow-to-Depth Proposals [65.24533384679657]
  We present an approach with a differentiable flow-to-depth layer for video depth estimation. The model consists of a flow-to-depth layer, a camera pose refinement module, and a depth fusion network. Our approach outperforms state-of-the-art depth estimation methods, and has reasonable cross dataset generalization capability.
  arXiv  Detail & Related papers  (2019-12-30T10:45:57Z)

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.