{"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/leveraging-shape-completion-for-3d-siamese","title":"Leveraging Shape Completion for 3D Siamese Tracking","arxiv_id":"1903.01784","date":"2019-03-05","proceeding":"CVPR 2019 6","authors":["Silvio Giancola","Jesus Zarzar","Bernard Ghanem"],"abstract":"Point clouds are challenging to process due to their sparsity, therefore\nautonomous vehicles rely more on appearance attributes than pure geometric\nfeatures. However, 3D LIDAR perception can provide crucial information for\nurban navigation in challenging light or weather conditions. In this paper, we\ninvestigate the versatility of Shape Completion for 3D Object Tracking in LIDAR\npoint clouds. We design a Siamese tracker that encodes model and candidate\nshapes into a compact latent representation. We regularize the encoding by\nenforcing the latent representation to decode into an object model shape. We\nobserve that 3D object tracking and 3D shape completion complement each other.\nLearning a more meaningful latent representation shows better discriminatory\ncapabilities, leading to improved tracking performance. We test our method on\nthe KITTI Tracking set using car 3D bounding boxes. Our model reaches a 76.94%\nSuccess rate and 81.38% Precision for 3D Object Tracking, with the shape\ncompletion regularization leading to an improvement of 3% in both metrics.","url_abs":"http://arxiv.org/abs/1903.01784v2","url_pdf":"http://arxiv.org/pdf/1903.01784v2.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":"leveraging-shape-completion-for-3d-siamese","repo_url":"https://github.com/SilvioGiancola/ShapeCompletion3DTracking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-object-tracking","task_name":"3D Object Tracking"},{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.01784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.01784"}},"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/SilvioGiancola/ShapeCompletion3DTracking","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"339bd8460d492f7b","entry":"verbosify","repo":"SilvioGiancola/ShapeCompletion3DTracking","repo_kind":"official","path":"pretraining/trainAE_main.py","file_url":"https://github.com/SilvioGiancola/ShapeCompletion3DTracking/blob/HEAD/pretraining/trainAE_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"339bd8460d492f7b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}