{"id":"W4386597045","doi":"10.1109/icip49359.2023.10222432","title":"Learning Disentangled Features for Nerf-Based Face Reconstruction","year":2023,"lang":"en","type":"article","venue":"","topic":"Face recognition and analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Face (sociological concept); Overfitting; Rendering (computer graphics); Computer vision; Deep learning; Iterative reconstruction; Segmentation; Encoder; Autoencoder; Artificial neural network","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":[0.0007552368,0.001040741,0.00102424,0.0008121963,0.0002743385,0.0006903477,0.001495227,0.001052305,0.0043415],"category_scores_gemma":[0.002110499,0.0006007857,0.001237643,0.0005326792,0.0005300567,0.001261589,0.001493318,0.001876508,0.002177904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005239837,"about_ca_system_score_gemma":0.0006502523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003400432,"about_ca_topic_score_gemma":0.005369623,"domain_scores_codex":[0.9995701,0.00006121364,0.0000142849,0.0001285323,0.0001715936,0.00005425743],"domain_scores_gemma":[0.9996079,0.0001107616,0.00003334579,0.0001296962,0.00009389289,0.00002445652],"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":[0.0002220515,0.000143912,0.001435245,0.00009881165,0.0001172449,0.0001783687,0.00009290679,0.3022854,0.02378981,0.007021907,0.007471805,0.6571426],"study_design_scores_gemma":[0.000005330541,0.00002329962,0.0001759642,0.000007952026,0.000008718813,0.0001278203,0.00001284403,0.9907361,0.005494494,0.002501306,0.0008972731,0.000008989094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01036716,0.0001614702,0.9868388,0.00007771549,0.00002979058,0.00003335585,0.0001190019,0.001544708,0.000827897],"genre_scores_gemma":[0.3435873,0.000495671,0.6447136,0.0003770168,0.00006781225,0.0001733543,0.00192774,0.0007591835,0.0078982],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0043415,"threshold_uncertainty_score":0.0145238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01707882511245495,"score_gpt":0.257548274805443,"score_spread":0.240469449692988,"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."}}