{"id":"W2902375431","doi":"10.1145/3272127.3275017","title":"Practical SVBRDF acquisition of 3D objects with unstructured flash photography","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; H2020 European Research Council; Samsung; Defense Advanced Research Projects Agency; Ministerio de Economía y Competitividad; Korea Creative Content Agency; National Research Foundation of Korea; Ministry of Science and ICT, South Korea; European Commission","keywords":"Computer science; Rendering (computer graphics); Computer vision; Artificial intelligence; Computer graphics (images); 3D reconstruction; Flash (photography); Graphics pipeline; Photography; Photometric stereo; Computer graphics; 3D computer graphics; Optics; Image (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":[0.0001177911,0.000168084,0.0001673019,0.0004260091,0.0002581039,0.00005691708,0.0004603619,0.00007824336,0.00005190477],"category_scores_gemma":[0.00002269342,0.000139777,0.00009374208,0.001579563,0.0003324781,0.0006867714,0.00001251475,0.0002804219,0.00001627449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001289537,"about_ca_system_score_gemma":0.00006923839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007345977,"about_ca_topic_score_gemma":0.00004354945,"domain_scores_codex":[0.9987139,0.00005873752,0.0002137528,0.0003789683,0.0003900398,0.0002446185],"domain_scores_gemma":[0.9984454,0.0001566828,0.0001159951,0.0009139316,0.0002624849,0.000105488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00146024,0.002857261,0.001967429,0.0002351957,0.0008790143,0.0001237038,0.007652695,0.0008560651,0.06987259,0.09886396,0.001650539,0.8135813],"study_design_scores_gemma":[0.00872669,0.009244428,0.01995574,0.000880674,0.0004006743,0.0009850947,0.0009043899,0.135017,0.6694465,0.1312857,0.02030102,0.002852099],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006221927,0.00001279293,0.991662,0.0008968251,0.0002850955,0.0001505714,0.000008398388,0.0001637773,0.000598621],"genre_scores_gemma":[0.6054937,0.00003465921,0.3937863,0.0006343399,0.00002011048,0.000007267256,0.000001297329,0.000009799469,0.00001244248],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8107292,"threshold_uncertainty_score":0.569994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01732117244825623,"score_gpt":0.2913250442058272,"score_spread":0.2740038717575709,"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."}}