{"id":"W2986869486","doi":"10.48550/arxiv.1911.07262","title":"Leveraging Multi-view Image Sets for Unsupervised Intrinsic Image Decomposition and Highlight Separation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Decomposition; Image (mathematics); Computer vision; Object (grammar); Representation (politics); Pattern recognition (psychology); Exploit; Construct (python library); Range (aeronautics)","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":[0.0005567258,0.001148111,0.0008070348,0.0009217014,0.0002938061,0.0007413836,0.001170217,0.000740932,0.001160986],"category_scores_gemma":[0.00134043,0.0005331933,0.001100124,0.0007817176,0.0005307022,0.001085275,0.001277013,0.001611192,0.00126474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003039188,"about_ca_system_score_gemma":0.0005226117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001870573,"about_ca_topic_score_gemma":0.00587419,"domain_scores_codex":[0.9995797,0.00006739336,0.00001515335,0.0001661153,0.0001118618,0.00005977044],"domain_scores_gemma":[0.9991968,0.0001631627,0.00009324495,0.0003096316,0.0001736016,0.00006356546],"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":[0.0003137313,0.0003235664,0.003059511,0.0002215022,0.0001961601,0.0001447559,0.0001943296,0.07996453,0.2824627,0.004297481,0.006458024,0.6223636],"study_design_scores_gemma":[0.0000200503,0.0001352863,0.00351814,0.00002325321,0.00005678873,0.0002678937,0.00005984133,0.8934191,0.0925712,0.004209609,0.005687863,0.00003100835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02910104,0.0002121187,0.9673946,0.0000755474,0.00002888678,0.00004910443,0.0001977003,0.001776654,0.001164345],"genre_scores_gemma":[0.2504342,0.0003711357,0.7434033,0.0001825876,0.00006644391,0.0001055632,0.001715598,0.0004928879,0.003228304],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001870573,"threshold_uncertainty_score":0.003883839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0612175971287641,"score_gpt":0.254307548921901,"score_spread":0.193089951793137,"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."}}