{"title":"用于立体视差贴图细化的各向异性中值滤波","authors":"Nils Einecke, J. Eggert","doi":"10.5220/0004200401890198","DOIUrl":null,"url":null,"abstract":"In this paper we present a novel method for refining stereo disparity maps that is inspired by both simple median filtering and edge-preserving anisotropic filtering. We argue that a combination of these two techniques is particularly effective for reducing the fattening effect that typically occurs for block-matching stereo algorithms. Experiments show that the newly proposed post-refinement can propel simple patch-based algorithms to much higher ranks in the Middlebury stereo benchmark. Furthermore, a comparison to state-of-the-art methods for disparity refinement shows a similar accuracy improvement but at only a fraction of the computational effort. Hence, this approach can be used in systems with restricted computational power.","PeriodicalId":411140,"journal":{"name":"International Conference on Computer Vision Theory and Applications","volume":"91 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"22","resultStr":"{\"title\":\"Anisotropic Median Filtering for Stereo Disparity Map Refinement\",\"authors\":\"Nils Einecke, J. Eggert\",\"doi\":\"10.5220/0004200401890198\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper we present a novel method for refining stereo disparity maps that is inspired by both simple median filtering and edge-preserving anisotropic filtering. We argue that a combination of these two techniques is particularly effective for reducing the fattening effect that typically occurs for block-matching stereo algorithms. Experiments show that the newly proposed post-refinement can propel simple patch-based algorithms to much higher ranks in the Middlebury stereo benchmark. Furthermore, a comparison to state-of-the-art methods for disparity refinement shows a similar accuracy improvement but at only a fraction of the computational effort. Hence, this approach can be used in systems with restricted computational power.\",\"PeriodicalId\":411140,\"journal\":{\"name\":\"International Conference on Computer Vision Theory and Applications\",\"volume\":\"91 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-08-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"22\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Conference on Computer Vision Theory and Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5220/0004200401890198\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Computer Vision Theory and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5220/0004200401890198","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Anisotropic Median Filtering for Stereo Disparity Map Refinement
In this paper we present a novel method for refining stereo disparity maps that is inspired by both simple median filtering and edge-preserving anisotropic filtering. We argue that a combination of these two techniques is particularly effective for reducing the fattening effect that typically occurs for block-matching stereo algorithms. Experiments show that the newly proposed post-refinement can propel simple patch-based algorithms to much higher ranks in the Middlebury stereo benchmark. Furthermore, a comparison to state-of-the-art methods for disparity refinement shows a similar accuracy improvement but at only a fraction of the computational effort. Hence, this approach can be used in systems with restricted computational power.