CbwLoss: Constrained Bidirectional Weighted Loss for Self-supervised Learning of Depth and Pose

• URL: http://arxiv.org/abs/2212.05845v1
• Date: Mon, 12 Dec 2022 12:18:24 GMT
• Title: CbwLoss: Constrained Bidirectional Weighted Loss for Self-supervised Learning of Depth and Pose
• Authors: Fei Wang, Jun Cheng, Penglei Liu
• Abstract summary: Photometric differences are used to train neural networks for estimating depth and camera pose from unlabeled monocular videos. In this paper, we deal with moving objects and occlusions utilizing the difference of the flow fields and depth structure generated by affine transformation and view synthesis. We mitigate the effect of textureless regions on model optimization by measuring differences between features with more semantic and contextual information without adding networks.
• Score: 13.581694284209885
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos. However, this approach is detrimental for model optimization because occlusions and moving objects in a scene violate the underlying static scenario assumption. In addition, pixels in textureless regions or less discriminative pixels hinder model training. To solve these problems, in this paper, we deal with moving objects and occlusions utilizing the difference of the flow fields and depth structure generated by affine transformation and view synthesis, respectively. Secondly, we mitigate the effect of textureless regions on model optimization by measuring differences between features with more semantic and contextual information without adding networks. In addition, although the bidirectionality component is used in each sub-objective function, a pair of images are reasoned about only once, which helps reduce overhead. Extensive experiments and visual analysis demonstrate the effectiveness of the proposed method, which outperform existing state-of-the-art self-supervised methods under the same conditions and without introducing additional auxiliary information.

Related papers

• Towards Cross-View-Consistent Self-Supervised Surround Depth Estimation [9.569646683579899]
  Self-Supervised Surround Depth Estimation from consecutive images offers an economical alternative. Previous SSSDE methods have proposed different mechanisms to fuse information across images, but few of them explicitly consider the cross-view constraints. This paper proposes an efficient and consistent pose estimation design and two loss functions to enhance cross-view consistency for SSSDE.
  arXiv  Detail & Related papers  (2024-07-04T16:29:05Z)
• Exploiting the Distortion-Semantic Interaction in Fisheye Data [12.633032175875865]
  Fisheye data has the wider field of view advantage over other types of cameras, but this comes at the expense of high distortion. objects further from the center exhibit deformations that make it difficult for a model to identify their semantic context. We introduce an approach to exploit this relationship by first extracting distortion class labels based on an object's distance from the center of the image. We then shape a backbone's representation space with a weighted contrastive loss that constrains objects of the same semantic class and distortion class to be close to each other.
  arXiv  Detail & Related papers  (2023-04-28T20:23:38Z)
• Parallax-Tolerant Unsupervised Deep Image Stitching [57.76737888499145]
  We propose UDIS++, a parallax-tolerant unsupervised deep image stitching technique. First, we propose a robust and flexible warp to model the image registration from global homography to local thin-plate spline motion. To further eliminate the parallax artifacts, we propose to composite the stitched image seamlessly by unsupervised learning for seam-driven composition masks.
  arXiv  Detail & Related papers  (2023-02-16T10:40:55Z)
• FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation [17.572459787107427]
  We propose a flow distillation loss to replace the typical photometric loss and a prior flow based mask to remove invalid pixels. Our approach achieves state-of-the-art results on both KITTI and NYU-Depth-v2 datasets.
  arXiv  Detail & Related papers  (2023-01-20T04:02:13Z)
• Frequency-Aware Self-Supervised Monocular Depth Estimation [41.97188738587212]
  We present two versatile methods to enhance self-supervised monocular depth estimation models. The high generalizability of our methods is achieved by solving the fundamental and ubiquitous problems in photometric loss function. We are the first to propose blurring images to improve depth estimators with an interpretable analysis.
  arXiv  Detail & Related papers  (2022-10-11T14:30:26Z)
• RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation [110.4255414234771]
  Existing solutions require massive training data or lack generalizability to unknown rendering configurations. We propose a novel approach that marries domain randomization and differentiable rendering gradients to address this problem. Our approach achieves significantly lower reconstruction errors and has better generalizability among unknown rendering configurations.
  arXiv  Detail & Related papers  (2022-05-11T17:59:51Z)
• Degradation-agnostic Correspondence from Resolution-asymmetric Stereo [96.03964515969652]
  We study the problem of stereo matching from a pair of images with different resolutions, e.g., those acquired with a tele-wide camera system. We propose to impose the consistency between two views in a feature space instead of the image space, named feature-metric consistency. We find that, although a stereo matching network trained with the photometric loss is not optimal, its feature extractor can produce degradation-agnostic and matching-specific features.
  arXiv  Detail & Related papers  (2022-04-04T12:24:34Z)
• Efficient and Differentiable Shadow Computation for Inverse Problems [64.70468076488419]
  Differentiable geometric computation has received increasing interest for image-based inverse problems. We propose an efficient yet efficient approach for differentiable visibility and soft shadow computation. As our formulation is differentiable, it can be used to solve inverse problems such as texture, illumination, rigid pose, and deformation recovery from images.
  arXiv  Detail & Related papers  (2021-04-01T09:29:05Z)
• SIR: Self-supervised Image Rectification via Seeing the Same Scene from Multiple Different Lenses [82.56853587380168]
  We propose a novel self-supervised image rectification (SIR) method based on an important insight that the rectified results of distorted images of the same scene from different lens should be the same. We leverage a differentiable warping module to generate the rectified images and re-distorted images from the distortion parameters. Our method achieves comparable or even better performance than the supervised baseline method and representative state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-11-30T08:23:25Z)
• Feature-metric Loss for Self-supervised Learning of Depth and Egomotion [13.995413542601472]
  Photometric loss is widely used for self-supervised depth and egomotion estimation. In this work, feature-metric loss is proposed and defined on feature representation. Comprehensive experiments and detailed analysis via visualization demonstrate the effectiveness of the proposed feature-metric loss.
  arXiv  Detail & Related papers  (2020-07-21T05:19:07Z)
• Self-Supervised Linear Motion Deblurring [112.75317069916579]
  Deep convolutional neural networks are state-of-the-art for image deblurring. We present a differentiable reblur model for self-supervised motion deblurring. Our experiments demonstrate that self-supervised single image deblurring is really feasible.
  arXiv  Detail & Related papers  (2020-02-10T20:15:21Z)

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.