{"id":"W4392815296","doi":"10.1016/j.neucom.2024.127553","title":"Multi-view 3D reconstruction based on deep learning: A survey and comparison of methods","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Science and Technology Planning Project of Guangdong Province; Basic and Applied Basic Research Foundation of Guangdong Province; Guangzhou Science and Technology Program key projects; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Point cloud; Artificial intelligence; Field (mathematics); Deep learning; Exploit; 3D reconstruction; Feature (linguistics); Key (lock); Matching (statistics); Machine learning; Voxel; Computer vision; Pattern recognition (psychology)","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":[0.0008618257,0.000125013,0.0002217143,0.0001706107,0.0001260547,0.0001366686,0.0002038455,0.00003079946,0.000003445199],"category_scores_gemma":[0.0002987864,0.0001164885,0.00004274779,0.0004724227,0.00003806109,0.0001898483,0.0001419912,0.0003423392,0.000005178443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001426337,"about_ca_system_score_gemma":0.00002225902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008238562,"about_ca_topic_score_gemma":0.000001458306,"domain_scores_codex":[0.9983829,0.0005771484,0.0003022219,0.000442495,0.0001199183,0.0001753059],"domain_scores_gemma":[0.9984805,0.001107402,0.000106579,0.0001918717,0.00005503426,0.0000586133],"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":[0.000002549736,0.00001946858,0.00564119,0.00005195496,0.000002642991,0.000002140689,0.0001651204,0.01048337,0.002234752,0.00008478414,0.000005841482,0.9813062],"study_design_scores_gemma":[0.0001579856,0.00008537184,0.01388431,0.0001693032,0.000002516479,0.00001595041,0.00001338275,0.9829707,0.001149807,0.0000242686,0.001423379,0.0001030029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009088133,0.00052461,0.9892413,0.00007631737,0.0005102184,0.00009186425,2.524244e-7,0.0002325489,0.0002347272],"genre_scores_gemma":[0.4201609,0.000009336021,0.5797076,0.00008600249,0.00001632621,9.266163e-7,6.107899e-7,0.000008723612,0.000009588564],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9812032,"threshold_uncertainty_score":0.4750263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.074760995575194,"score_gpt":0.4106405939045615,"score_spread":0.3358795983293675,"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."}}