{"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/lost-appearance-invariant-place-recognition","title":"LoST? Appearance-Invariant Place Recognition for Opposite Viewpoints using Visual Semantics","arxiv_id":"1804.05526","date":"2018-04-16","proceeding":null,"authors":["Sourav Garg","Niko Suenderhauf","Michael Milford"],"abstract":"Human visual scene understanding is so remarkable that we are able to\nrecognize a revisited place when entering it from the opposite direction it was\nfirst visited, even in the presence of extreme variations in appearance. This\ncapability is especially apparent during driving: a human driver can recognize\nwhere they are when travelling in the reverse direction along a route for the\nfirst time, without having to turn back and look. The difficulty of this\nproblem exceeds any addressed in past appearance- and viewpoint-invariant\nvisual place recognition (VPR) research, in part because large parts of the\nscene are not commonly observable from opposite directions. Consequently, as\nshown in this paper, the precision-recall performance of current\nstate-of-the-art viewpoint- and appearance-invariant VPR techniques is orders\nof magnitude below what would be usable in a closed-loop system. Current\nengineered solutions predominantly rely on panoramic camera or LIDAR sensing\nsetups; an eminently suitable engineering solution but one that is clearly very\ndifferent to how humans navigate, which also has implications for how naturally\nhumans could interact and communicate with the navigation system. In this paper\nwe develop a suite of novel semantic- and appearance-based techniques to enable\nfor the first time high performance place recognition in this challenging\nscenario. We first propose a novel Local Semantic Tensor (LoST) descriptor of\nimages using the convolutional feature maps from a state-of-the-art dense\nsemantic segmentation network. Then, to verify the spatial semantic arrangement\nof the top matching candidates, we develop a novel approach for mining\nsemantically-salient keypoint correspondences.","url_abs":"http://arxiv.org/abs/1804.05526v3","url_pdf":"http://arxiv.org/pdf/1804.05526v3.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":"lost-appearance-invariant-place-recognition","repo_url":"https://github.com/oravus/lostX","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"visual-place-recognition","task_name":"Visual Place Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.05526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.05526"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/oravus/lostX","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"ca87b58f6b293f90","entry":"filter_kp_semantically","repo":"oravus/lostX","repo_kind":"official","path":"lost_kc/match_lost_kc.py","file_url":"https://github.com/oravus/lostX/blob/HEAD/lost_kc/match_lost_kc.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":"ca87b58f6b293f90"}},{"code_sha256_prefix":"5e25b55783988632","entry":"getEncoding","repo":"oravus/lostX","repo_kind":"official","path":"lost_kc/LoST.py","file_url":"https://github.com/oravus/lostX/blob/HEAD/lost_kc/LoST.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":"5e25b55783988632"}},{"code_sha256_prefix":"be4e8c4f8c531a31","entry":"getLocalCC","repo":"oravus/lostX","repo_kind":"official","path":"lost_kc/LoST.py","file_url":"https://github.com/oravus/lostX/blob/HEAD/lost_kc/LoST.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":"be4e8c4f8c531a31"}},{"code_sha256_prefix":"082ab413db2d6398","entry":"getTemporalMeanofClusterCenters","repo":"oravus/lostX","repo_kind":"official","path":"lost_kc/LoST.py","file_url":"https://github.com/oravus/lostX/blob/HEAD/lost_kc/LoST.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":"082ab413db2d6398"}},{"code_sha256_prefix":"7bf68a00679659e5","entry":"process_semScores","repo":"oravus/lostX","repo_kind":"official","path":"lost_kc/reformat_data.py","file_url":"https://github.com/oravus/lostX/blob/HEAD/lost_kc/reformat_data.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":"7bf68a00679659e5"}},{"code_sha256_prefix":"4221c670d1f0e29a","entry":"readDenseDesc","repo":"oravus/lostX","repo_kind":"official","path":"lost_kc/match_lost_kc.py","file_url":"https://github.com/oravus/lostX/blob/HEAD/lost_kc/match_lost_kc.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":"4221c670d1f0e29a"}},{"code_sha256_prefix":"d7d5acc0cab2f65c","entry":"unravel_flat_kp","repo":"oravus/lostX","repo_kind":"official","path":"lost_kc/match_lost_kc.py","file_url":"https://github.com/oravus/lostX/blob/HEAD/lost_kc/match_lost_kc.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":"d7d5acc0cab2f65c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}