{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fast-disparity-estimation-using-dense","title":"Fast Disparity Estimation using Dense Networks","arxiv_id":"1805.07499","date":"2018-05-19","proceeding":null,"authors":["Rowel Atienza"],"abstract":"Disparity estimation is a difficult problem in stereo vision because the\ncorrespondence technique fails in images with textureless and repetitive\nregions. Recent body of work using deep convolutional neural networks (CNN)\novercomes this problem with semantics. Most CNN implementations use an\nautoencoder method; stereo images are encoded, merged and finally decoded to\npredict the disparity map. In this paper, we present a CNN implementation\ninspired by dense networks to reduce the number of parameters. Furthermore, our\napproach takes into account semantic reasoning in disparity estimation. Our\nproposed network, called DenseMapNet, is compact, fast and can be trained\nend-to-end. DenseMapNet requires 290k parameters only and runs at 30Hz or\nfaster on color stereo images in full resolution. Experimental results show\nthat DenseMapNet accuracy is comparable with other significantly bigger\nCNN-based methods.","url_abs":"http://arxiv.org/abs/1805.07499v1","url_pdf":"http://arxiv.org/pdf/1805.07499v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fast-disparity-estimation-using-dense","repo_url":"https://github.com/roatienza/densemapnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"disparity-estimation","task_name":"Disparity Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}