Dazheng Zhou , Mingliang Zhang , Xianjie Gao , Youmei Zhang , Bin Li
{"title":"用于自监督单目深度估计的完整上下文信息提取","authors":"Dazheng Zhou , Mingliang Zhang , Xianjie Gao , Youmei Zhang , Bin Li","doi":"10.1016/j.cviu.2024.104032","DOIUrl":null,"url":null,"abstract":"<div><p>Self-supervised learning methods are increasingly important for monocular depth estimation since they do not require ground-truth data during training. Although existing methods have achieved great success for better monocular depth estimation based on Convolutional Neural Networks (CNNs), the limited receptive field of CNNs usually is insufficient to effectively model the global information, e.g., relationship between foreground and background or relationship among objects, which are crucial for accurately capturing scene structure. Recently, some studies based on Transformers have attracted significant interest in computer vision. However, duo to the lack of spatial locality bias, they may fail to model the local information, e.g., fine-grained details with an image. To tackle these issues, we propose a novel self-supervised learning framework by incorporating the advantages of both the CNNs and Transformers so as to model the complete contextual information for high-quality monocular depth estimation. Specifically, the proposed method mainly includes two branches, where the Transformer branch is considered to capture the global information while the Convolution branch is exploited to preserve the local information. We also design a rectangle convolution module with pyramid structure to perceive the semi-global information, e.g. thin objects, along the horizontal and vertical directions within an image. Moreover, we propose a shape refinement module by learning the affinity matrix between pixel and its neighborhood to obtain accurate geometrical structure of scenes. Extensive experiments evaluated on KITTI, Cityscapes and Make3D dataset demonstrate that the proposed method achieves the competitive result compared with the state-of-the-art self-supervised monocular depth estimation methods and shows good cross-dataset generalization ability.</p></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Complete contextual information extraction for self-supervised monocular depth estimation\",\"authors\":\"Dazheng Zhou , Mingliang Zhang , Xianjie Gao , Youmei Zhang , Bin Li\",\"doi\":\"10.1016/j.cviu.2024.104032\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Self-supervised learning methods are increasingly important for monocular depth estimation since they do not require ground-truth data during training. Although existing methods have achieved great success for better monocular depth estimation based on Convolutional Neural Networks (CNNs), the limited receptive field of CNNs usually is insufficient to effectively model the global information, e.g., relationship between foreground and background or relationship among objects, which are crucial for accurately capturing scene structure. Recently, some studies based on Transformers have attracted significant interest in computer vision. However, duo to the lack of spatial locality bias, they may fail to model the local information, e.g., fine-grained details with an image. To tackle these issues, we propose a novel self-supervised learning framework by incorporating the advantages of both the CNNs and Transformers so as to model the complete contextual information for high-quality monocular depth estimation. Specifically, the proposed method mainly includes two branches, where the Transformer branch is considered to capture the global information while the Convolution branch is exploited to preserve the local information. We also design a rectangle convolution module with pyramid structure to perceive the semi-global information, e.g. thin objects, along the horizontal and vertical directions within an image. Moreover, we propose a shape refinement module by learning the affinity matrix between pixel and its neighborhood to obtain accurate geometrical structure of scenes. Extensive experiments evaluated on KITTI, Cityscapes and Make3D dataset demonstrate that the proposed method achieves the competitive result compared with the state-of-the-art self-supervised monocular depth estimation methods and shows good cross-dataset generalization ability.</p></div>\",\"PeriodicalId\":50633,\"journal\":{\"name\":\"Computer Vision and Image Understanding\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-05-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computer Vision and Image Understanding\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1077314224001139\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Vision and Image Understanding","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1077314224001139","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
Complete contextual information extraction for self-supervised monocular depth estimation
Self-supervised learning methods are increasingly important for monocular depth estimation since they do not require ground-truth data during training. Although existing methods have achieved great success for better monocular depth estimation based on Convolutional Neural Networks (CNNs), the limited receptive field of CNNs usually is insufficient to effectively model the global information, e.g., relationship between foreground and background or relationship among objects, which are crucial for accurately capturing scene structure. Recently, some studies based on Transformers have attracted significant interest in computer vision. However, duo to the lack of spatial locality bias, they may fail to model the local information, e.g., fine-grained details with an image. To tackle these issues, we propose a novel self-supervised learning framework by incorporating the advantages of both the CNNs and Transformers so as to model the complete contextual information for high-quality monocular depth estimation. Specifically, the proposed method mainly includes two branches, where the Transformer branch is considered to capture the global information while the Convolution branch is exploited to preserve the local information. We also design a rectangle convolution module with pyramid structure to perceive the semi-global information, e.g. thin objects, along the horizontal and vertical directions within an image. Moreover, we propose a shape refinement module by learning the affinity matrix between pixel and its neighborhood to obtain accurate geometrical structure of scenes. Extensive experiments evaluated on KITTI, Cityscapes and Make3D dataset demonstrate that the proposed method achieves the competitive result compared with the state-of-the-art self-supervised monocular depth estimation methods and shows good cross-dataset generalization ability.
期刊介绍:
The central focus of this journal is the computer analysis of pictorial information. Computer Vision and Image Understanding publishes papers covering all aspects of image analysis from the low-level, iconic processes of early vision to the high-level, symbolic processes of recognition and interpretation. A wide range of topics in the image understanding area is covered, including papers offering insights that differ from predominant views.
Research Areas Include:
• Theory
• Early vision
• Data structures and representations
• Shape
• Range
• Motion
• Matching and recognition
• Architecture and languages
• Vision systems