{"corpus_id":199441943,"paper_sha":"4511f4100decc138031f93212cfd921bf42f72e2","doi":"10.1109/ICCV.2019.00939","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":2991216808,"dblp_id":"conf/iccv/BehleyGMQBSG19","acl_id":null,"title":"SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences","year":2019,"publication_date":"2019-04-02","venue":"IEEE International Conference on Computer Vision","journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","pages":"9296-9306","volume":null},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle","Conference"],"pubmed_pub_types":null,"s2_fields_of_study":["Computer Science","Engineering","Environmental Science"],"reference_count":67,"citation_count":2262,"influential_citation_count":523,"is_open_access":true,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":"https://arxiv.org/pdf/1904.01416","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/4511f4100decc138031f93212cfd921bf42f72e2","s2_open_access_license":null,"s2_open_access_status":"GREEN","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"Semantic scene understanding is important for various applications. In particular, self-driving cars need a fine-grained understanding of the surfaces and objects in their vicinity. Light detection and ranging (LiDAR) provides precise geometric information about the environment and is thus a part of the sensor suites of almost all self-driving cars. Despite the relevance of semantic scene understanding for this application, there is a lack of a large dataset for this task which is based on an automotive LiDAR. In this paper, we introduce a large dataset to propel research on laser-based semantic segmentation. We annotated all sequences of the KITTI Vision Odometry Benchmark and provide dense point-wise annotations for the complete 360-degree field-of-view of the employed automotive LiDAR. We propose three benchmark tasks based on this dataset: (i) semantic segmentation of point clouds using a single scan, (ii) semantic segmentation using multiple past scans, and (iii) semantic scene completion, which requires to anticipate the semantic scene in the future. We provide baseline experiments and show that there is a need for more sophisticated models to efficiently tackle these tasks. Our dataset opens the door for the development of more advanced methods, but also provides plentiful data to investigate new research directions.","claims":[{"public_id":"cl_d2f3e07733db241d97ad95bbca122e95","status":"active","text":"Baseline experiments show that more sophisticated models are needed to efficiently tackle the proposed tasks.","confidence":0.85,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_d2f3e07733db241d97ad95bbca122e95"},{"public_id":"cl_e4d653c9598d25564abd68f820a5a57d","status":"active","text":"SemanticKITTI provides dense point-wise annotations for the complete 360-degree field-of-view of the employed automotive LiDAR across all sequences of the KITTI Vision Odometry Benchmark.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_e4d653c9598d25564abd68f820a5a57d"},{"public_id":"cl_81035bf233a6d81f3140d5b698e86a87","status":"active","text":"Three benchmark tasks are proposed: semantic segmentation of point clouds using a single scan, semantic segmentation using multiple past scans, and semantic scene completion.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_81035bf233a6d81f3140d5b698e86a87"}],"concepts":[{"public_id":"co_039526e77d694fd18f97b481595e5506","status":"active","name":"semantic segmentation using multiple past scans","description":"A benchmark task that requires semantic segmentation using multiple past LiDAR scans.","types":["task"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_039526e77d694fd18f97b481595e5506"},{"public_id":"co_2939bf63736f565a1b340472cb3d6eb0","status":"active","name":"semantic scene completion","description":"A benchmark task that requires anticipating the semantic scene in the future.","types":["task"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_2939bf63736f565a1b340472cb3d6eb0"},{"public_id":"co_9d0d261bedae6e77374fefde511f7b11","status":"active","name":"KITTI Vision Odometry Benchmark","description":"The benchmark whose sequences are fully annotated in the SemanticKITTI dataset.","types":["benchmark"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_9d0d261bedae6e77374fefde511f7b11"},{"public_id":"co_abb34304e1e0d06631699bfad1fa3676","status":"active","name":"baseline experiments","description":"Experiments conducted on the SemanticKITTI dataset to establish baseline performance for the proposed tasks.","types":["experiment"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_abb34304e1e0d06631699bfad1fa3676"},{"public_id":"co_b4490f1f1f0d08ba35dc1b741ead4513","status":"active","name":"SemanticKITTI","description":"A large dataset for laser-based semantic segmentation, providing dense point-wise annotations for the complete 360-degree field-of-view of an automotive LiDAR, based on the KITTI Vision Odometry Benchmark sequences.","types":["dataset"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_b4490f1f1f0d08ba35dc1b741ead4513"},{"public_id":"co_cb06ac0eb57037ed3ef6d2cde54c23f1","status":"active","name":"semantic segmentation of point clouds using a single scan","description":"A benchmark task that requires semantic segmentation of a point cloud from a single LiDAR scan.","types":["task"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_cb06ac0eb57037ed3ef6d2cde54c23f1"},{"public_id":"co_d480688e4a2f665344c6286d1aa3ac27","status":"active","name":"dense point-wise annotations","description":"Annotations that label every point in the LiDAR point cloud with a semantic class.","types":["annotation"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_d480688e4a2f665344c6286d1aa3ac27"},{"public_id":"co_e27497c6b0a321f2fe21422117e5f519","status":"active","name":"automotive LiDAR","description":"The type of LiDAR sensor employed in the dataset, providing precise geometric information for self-driving cars.","types":["sensor"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_e27497c6b0a321f2fe21422117e5f519"}],"external_ids":{"DOI":"10.1109/ICCV.2019.00939","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":2991216808,"DBLP":"conf/iccv/BehleyGMQBSG19","ACL":null},"open_access":{"is_open_access":true,"pdf_url":"https://arxiv.org/pdf/1904.01416","landing_url":"https://www.semanticscholar.org/paper/4511f4100decc138031f93212cfd921bf42f72e2","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":null,"status":"GREEN","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":636000,"paper_uid":"8769e227-3387-46a1-8b55-22165df0b095","canonical_identity":{"paper_id":636000,"paper_uid":"8769e227-3387-46a1-8b55-22165df0b095","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/199441943"}