{"id":"W2165192967","doi":"10.1109/tpami.2005.158","title":"Example-based photometric stereo: shape reconstruction with general, varying BRDFs","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":308,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Office of Naval Research; Microsoft; National Science Foundation","keywords":"Computer vision; Artificial intelligence; Photometric stereo; Computer science; Segmentation; Calibration; Sequence (biology); Simple (philosophy); Image segmentation; Computer graphics (images); Image (mathematics); Geometry; 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":[0.0002888246,0.0002459443,0.0002936892,0.00185119,0.0002464711,0.0003047313,0.0004159682,0.00006477698,0.0001420842],"category_scores_gemma":[0.000001659289,0.0002081323,0.0001809556,0.003420091,0.00005882883,0.0003033769,0.000006194608,0.0002122535,0.000006717044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004085117,"about_ca_system_score_gemma":0.00002781564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008080385,"about_ca_topic_score_gemma":0.0005491911,"domain_scores_codex":[0.9983259,0.0001007642,0.0003957706,0.0006322183,0.0003142203,0.0002310643],"domain_scores_gemma":[0.9989291,0.0001335997,0.0001442239,0.0005281863,0.0001338344,0.0001310629],"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":[0.00001201608,0.0001418114,0.00148041,0.00001070669,0.000215668,0.00000316684,0.00009163909,0.01749113,0.0001492195,0.0003961546,0.000003340565,0.9800047],"study_design_scores_gemma":[0.0001187988,0.0001831795,0.0005606196,0.00002489074,0.0001448811,0.00002125541,0.000003640755,0.8870454,0.1114035,0.00009533597,0.0001390795,0.0002593137],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01820378,0.00006671743,0.9810721,0.0001541555,0.00008748788,0.0001503333,0.0000112845,0.0002020264,0.00005207468],"genre_scores_gemma":[0.9730456,0.0002339529,0.02586769,0.0007333785,0.00002803986,0.00003090142,0.000004248363,0.00001356551,0.00004260432],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9797454,"threshold_uncertainty_score":0.8487388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03193799847270146,"score_gpt":0.2839978282215181,"score_spread":0.2520598297488167,"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."}}