{"id":"W3214794298","doi":"10.1109/cvpr52688.2022.01239","title":"Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Point cloud; Artificial intelligence; Object (grammar); Pairwise comparison; Generalization; Focus (optics); Task (project management); Computer vision; Pattern recognition (psychology); Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001475018,0.001535458,0.001202852,0.000831083,0.0005140667,0.0008184844,0.004213427,0.002257291,0.003219479],"category_scores_gemma":[0.003038601,0.001049728,0.00167536,0.0008414392,0.00151221,0.001426419,0.002623024,0.002531542,0.001643103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001175444,"about_ca_system_score_gemma":0.0008102279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003931706,"about_ca_topic_score_gemma":0.005869636,"domain_scores_codex":[0.9993311,0.0001588487,0.00002270412,0.0002395666,0.0001694707,0.00007827921],"domain_scores_gemma":[0.9986733,0.0005135699,0.0001514731,0.0004289997,0.0001454048,0.00008735155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001543023,0.0001083578,0.001420468,0.00006649749,0.00007803581,0.0001097059,0.00006453245,0.8627792,0.004185308,0.003570318,0.006118098,0.1213451],"study_design_scores_gemma":[0.000005649446,0.00002379255,0.0001012358,0.000004517217,0.000003486576,0.00002125829,0.000005082168,0.9969082,0.0008408096,0.00165348,0.0004289082,0.000003561108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03981395,0.0003800287,0.9500476,0.0003706493,0.0001098768,0.0001364956,0.0004603693,0.006019409,0.00266159],"genre_scores_gemma":[0.633459,0.0002477346,0.3507187,0.001014853,0.0001383435,0.0004178963,0.003559436,0.0009616974,0.009482389],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004213427,"threshold_uncertainty_score":0.01077026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02595872707432596,"score_gpt":0.2313729637842462,"score_spread":0.2054142367099202,"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."}}