{"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/segstereo-exploiting-semantic-information-for","title":"SegStereo: Exploiting Semantic Information for Disparity Estimation","arxiv_id":"1807.11699","date":"2018-07-31","proceeding":"ECCV 2018 9","authors":["Guorun Yang","Hengshuang Zhao","Jianping Shi","Zhidong Deng","Jiaya Jia"],"abstract":"Disparity estimation for binocular stereo images finds a wide range of\napplications. Traditional algorithms may fail on featureless regions, which\ncould be handled by high-level clues such as semantic segments. In this paper,\nwe suggest that appropriate incorporation of semantic cues can greatly rectify\nprediction in commonly-used disparity estimation frameworks. Our method\nconducts semantic feature embedding and regularizes semantic cues as the loss\nterm to improve learning disparity. Our unified model SegStereo employs\nsemantic features from segmentation and introduces semantic softmax loss, which\nhelps improve the prediction accuracy of disparity maps. The semantic cues work\nwell in both unsupervised and supervised manners. SegStereo achieves\nstate-of-the-art results on KITTI Stereo benchmark and produces decent\nprediction on both CityScapes and FlyingThings3D datasets.","url_abs":"http://arxiv.org/abs/1807.11699v1","url_pdf":"http://arxiv.org/pdf/1807.11699v1.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":[],"tasks":[{"task_slug":"disparity-estimation","task_name":"Disparity Estimation"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-kitti-semantic","task":"Semantic Segmentation","dataset":"KITTI Semantic Segmentation","model":"SegStereo","rank_in_archive_order":6,"of":7,"metrics":{"Mean IoU (class)":"59.10"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.11699","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}