Geometry-based Occlusion-Aware Unsupervised Stereo Matching for Autonomous Driving

• URL: http://arxiv.org/abs/2010.10700v1
• Date: Wed, 21 Oct 2020 01:22:55 GMT
• Title: Geometry-based Occlusion-Aware Unsupervised Stereo Matching for Autonomous Driving
• Authors: Liang Peng, Dan Deng, and Deng Cai
• Abstract summary: Occlusion handling is a challenging problem in stereo matching, especially for unsupervised methods. We introduce an effective way to detect occluded regions and propose a novel unsupervised training strategy to deal with occluded regions. Our method significantly outperforms the other unsupervised methods for stereo matching.
• Score: 26.787020338316815
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, there are emerging many stereo matching methods for autonomous driving based on unsupervised learning. Most of them take advantage of reconstruction losses to remove dependency on disparity groundtruth. Occlusion handling is a challenging problem in stereo matching, especially for unsupervised methods. Previous unsupervised methods failed to take full advantage of geometry properties in occlusion handling. In this paper, we introduce an effective way to detect occlusion regions and propose a novel unsupervised training strategy to deal with occlusion that only uses the predicted left disparity map, by making use of its geometry features in an iterative way. In the training process, we regard the predicted left disparity map as pseudo groundtruth and infer occluded regions using geometry features. The resulting occlusion mask is then used in either training, post-processing, or both of them as guidance. Experiments show that our method could deal with the occlusion problem effectively and significantly outperforms the other unsupervised methods for stereo matching. Moreover, our occlusion-aware strategies can be extended to the other stereo methods conveniently and improve their performances.

Related papers

• Pseudo-Stereo Inputs: A Solution to the Occlusion Challenge in Self-Supervised Stereo Matching [0.0]
  Self-supervised stereo matching holds great promise for application and research. Direct self-supervised stereo matching paradigms based on photometric loss functions have consistently struggled with performance issues. We propose a simple yet highly effective pseudo-stereo inputs strategy to address the core occlusion challenge.
  arXiv  Detail & Related papers  (2024-10-03T14:40:17Z)
• Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency [31.261772846687297]
  We propose a method to identify and filter errors in the pseudo-depth map using multiple disparity maps. Experimental results show that the proposed method outperforms the previous methods.
  arXiv  Detail & Related papers  (2024-01-22T15:05:05Z)
• Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps [13.6555672824229]
  We present an unsupervised few-shot learning method via deep Laplacian eigenmaps. Our method learns representation from unlabeled data by grouping similar samples together. We analytically show how deep Laplacian eigenmaps avoid collapsed representation in unsupervised learning.
  arXiv  Detail & Related papers  (2022-10-07T14:53:03Z)
• Self-supervised Transformer for Deepfake Detection [112.81127845409002]
  Deepfake techniques in real-world scenarios require stronger generalization abilities of face forgery detectors. Inspired by transfer learning, neural networks pre-trained on other large-scale face-related tasks may provide useful features for deepfake detection. In this paper, we propose a self-supervised transformer based audio-visual contrastive learning method.
  arXiv  Detail & Related papers  (2022-03-02T17:44:40Z)
• Block shuffling learning for Deepfake Detection [9.180904212520355]
  Deepfake detection methods based on convolutional neural networks (CNN) have demonstrated high accuracy. These methods often suffer from decreased performance when faced with unknown forgery methods and common transformations. We propose a novel block shuffling regularization method to address this issue.
  arXiv  Detail & Related papers  (2022-02-06T17:16:46Z)
• Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection [97.93062818228015]
  We propose to integrate the reconstruction-based functionality into a novel self-supervised predictive architectural building block. Our block is equipped with a loss that minimizes the reconstruction error with respect to the masked area in the receptive field. We demonstrate the generality of our block by integrating it into several state-of-the-art frameworks for anomaly detection on image and video.
  arXiv  Detail & Related papers  (2021-11-17T13:30:31Z)
• Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation [64.92152574895111]
  We propose a simple Orthogonal Jacobian Regularization (OroJaR) to encourage deep generative model to learn disentangled representations. Our method is effective in disentangled and controllable image generation, and performs favorably against the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-08-17T15:01:46Z)
• Locality-aware Channel-wise Dropout for Occluded Face Recognition [116.2355331029041]
  Face recognition is a challenging task in unconstrained scenarios, especially when faces are partially occluded. We propose a novel and elegant occlusion-simulation method via dropping the activations of a group of neurons in some elaborately selected channel. Experiments on various benchmarks show that the proposed method outperforms state-of-the-art methods with a remarkable improvement.
  arXiv  Detail & Related papers  (2021-07-20T05:53:14Z)
• An Adaptive Framework for Learning Unsupervised Depth Completion [59.17364202590475]
  We present a method to infer a dense depth map from a color image and associated sparse depth measurements. We show that regularization and co-visibility are related via the fitness of the model to data and can be unified into a single framework.
  arXiv  Detail & Related papers  (2021-06-06T02:27:55Z)
• H-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry [4.968452390132676]
  We introduce the H-Net, a deep-learning framework for unsupervised stereo depth estimation. For the first time, a Siamese autoencoder architecture is used for depth estimation. Our method outperforms the state-ofthe-art unsupervised stereo depth estimation methods.
  arXiv  Detail & Related papers  (2021-04-22T19:16:35Z)
• Towards Certified Robustness of Distance Metric Learning [53.96113074344632]
  We advocate imposing an adversarial margin in the input space so as to improve the generalization and robustness of metric learning algorithms. We show that the enlarged margin is beneficial to the generalization ability by using the theoretical technique of algorithmic robustness.
  arXiv  Detail & Related papers  (2020-06-10T16:51:53Z)

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.