{"id":"W4387068241","doi":"10.1109/tpami.2023.3319448","title":"Deep Scene Flow Learning: From 2D Images to 3D Point Clouds","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Point cloud; Computer vision; Optical flow; Deep learning; Expediting; Motion estimation; Motion (physics); Point (geometry); Structure from motion; Task (project management); Compositing; Face (sociological concept); Image (mathematics); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002321191,0.0002441144,0.0003315665,0.000700308,0.0003174501,0.0002289053,0.0005297565,0.00004480146,0.0002996657],"category_scores_gemma":[0.00001550366,0.0002182833,0.0002230091,0.002262504,0.0000427999,0.0003226003,0.00002207192,0.0003460513,0.000433848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003220142,"about_ca_system_score_gemma":0.00001311836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007278419,"about_ca_topic_score_gemma":0.0003847008,"domain_scores_codex":[0.9981536,0.00009770144,0.0003584362,0.0007262949,0.0003251535,0.000338821],"domain_scores_gemma":[0.9988721,0.0001935819,0.00007336088,0.0005431673,0.00007933957,0.0002384195],"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":[0.000005747001,0.00003947861,0.0002753167,0.000002972592,0.0001210606,0.0000151249,0.0004658638,0.2245555,0.0007821879,0.000003738039,0.00001858911,0.7737144],"study_design_scores_gemma":[0.00006907673,0.00008129408,0.001283947,0.00002158269,0.0001143689,0.000003078654,0.0001030454,0.9400768,0.05744668,0.000241004,0.0003058105,0.0002533135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001083158,0.00008281659,0.9966456,0.001415683,0.0002714254,0.00009488252,0.00001823148,0.0003128817,0.00007528526],"genre_scores_gemma":[0.959606,0.000467335,0.03840874,0.001008972,0.00003029089,0.00001796783,0.00001099461,0.00001707878,0.0004326538],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9585228,"threshold_uncertainty_score":0.8901335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02006353029233907,"score_gpt":0.2872535069875473,"score_spread":0.2671899766952082,"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."}}