{"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/progressive-lidar-adaptation-for-road","title":"Progressive LiDAR Adaptation for Road Detection","arxiv_id":"1904.01206","date":"2019-04-02","proceeding":null,"authors":["Zhe Chen","Jing Zhang","DaCheng Tao"],"abstract":"Despite rapid developments in visual image-based road detection, robustly\nidentifying road areas in visual images remains challenging due to issues like\nillumination changes and blurry images. To this end, LiDAR sensor data can be\nincorporated to improve the visual image-based road detection, because LiDAR\ndata is less susceptible to visual noises. However, the main difficulty in\nintroducing LiDAR information into visual image-based road detection is that\nLiDAR data and its extracted features do not share the same space with the\nvisual data and visual features. Such gaps in spaces may limit the benefits of\nLiDAR information for road detection. To overcome this issue, we introduce a\nnovel Progressive LiDAR Adaptation-aided Road Detection (PLARD) approach to\nadapt LiDAR information into visual image-based road detection and improve\ndetection performance. In PLARD, progressive LiDAR adaptation consists of two\nsubsequent modules: 1) data space adaptation, which transforms the LiDAR data\nto the visual data space to align with the perspective view by applying\naltitude difference-based transformation; and 2) feature space adaptation,\nwhich adapts LiDAR features to visual features through a cascaded fusion\nstructure. Comprehensive empirical studies on the well-known KITTI road\ndetection benchmark demonstrate that PLARD takes advantage of both the visual\nand LiDAR information, achieving much more robust road detection even in\nchallenging urban scenes. In particular, PLARD outperforms other\nstate-of-the-art road detection models and is currently top of the publicly\naccessible benchmark leader-board.","url_abs":"http://arxiv.org/abs/1904.01206v1","url_pdf":"http://arxiv.org/pdf/1904.01206v1.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":"progressive-lidar-adaptation-for-road","repo_url":"https://github.com/zhechen/PLARD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.01206","atlas_url":"https://app.syntology.ai/?focus=1904.01206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01206"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhechen/PLARD","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"fe9eb7a22adf75a1","entry":"bootstrapped_cross_entropy2d","repo":"zhechen/PLARD","repo_kind":"official","path":"ptsemseg/loss.py","file_url":"https://github.com/zhechen/PLARD/blob/HEAD/ptsemseg/loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fe9eb7a22adf75a1"}},{"code_sha256_prefix":"31c592674a619dff","entry":"cross_entropy2d","repo":"zhechen/PLARD","repo_kind":"official","path":"ptsemseg/loss.py","file_url":"https://github.com/zhechen/PLARD/blob/HEAD/ptsemseg/loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31c592674a619dff"}},{"code_sha256_prefix":"54c382a189f6ba35","entry":"multi_scale_cross_entropy2d","repo":"zhechen/PLARD","repo_kind":"official","path":"ptsemseg/loss.py","file_url":"https://github.com/zhechen/PLARD/blob/HEAD/ptsemseg/loss.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54c382a189f6ba35"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}