{"id":"W3215295353","doi":"10.1145/3478513.3480529","title":"Keypoint-driven line drawing vectorization via PolyVector flow","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Vectorization (mathematics); Computer science; Raster graphics; Computer graphics (images); Spurious relationship; Animation; Set (abstract data type); Line (geometry); Topology (electrical circuits); Geometric primitive; Flow (mathematics); Task (project management); Geometry processing; Digital geometry; Computational geometry; Geometry; Algorithm; Artificial intelligence; Image processing; Mathematics; Image (mathematics); Digital image; Parallel computing","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009133919,0.002132259,0.001380523,0.003246726,0.0007599146,0.002794582,0.002818388,0.001159008,0.01089009],"category_scores_gemma":[0.003599175,0.0008694722,0.0009879157,0.002424153,0.0009176168,0.003039455,0.001933626,0.001670761,0.003912186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001118526,"about_ca_system_score_gemma":0.001201199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004484125,"about_ca_topic_score_gemma":0.005720711,"domain_scores_codex":[0.9989135,0.0001284486,0.00006045095,0.0003415256,0.0004615001,0.00009451859],"domain_scores_gemma":[0.9985505,0.0003159947,0.0002169531,0.0003021636,0.0005102346,0.0001041657],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000228156,0.0001251399,0.001344022,0.0002216689,0.00005844346,0.0001253259,0.0003304121,0.08227954,0.03724912,0.01500036,0.01198435,0.8510534],"study_design_scores_gemma":[0.00004940357,0.00008132356,0.0005747803,0.00002673373,0.00001737268,0.0001520346,0.00007925998,0.9429896,0.03319423,0.01203136,0.01075127,0.00005268566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003911303,0.00005615681,0.9853818,0.00004878663,0.00002876723,0.00007311556,0.0001295319,0.009820738,0.0005497978],"genre_scores_gemma":[0.09702009,0.0002292652,0.897908,0.00009034635,0.00004927703,0.0001697264,0.0009924201,0.001565008,0.001975932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01089009,"threshold_uncertainty_score":0.03643101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02310100960311167,"score_gpt":0.2783387597372208,"score_spread":0.2552377501341091,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}