{"id":"W2076491823","doi":"10.1145/2601097.2601206","title":"Intrinsic images in the wild","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":403,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Information and Intelligent Systems; Natural Sciences and Engineering Research Council of Canada; Intel Corporation","keywords":"Ground truth; Computer science; Crowdsourcing; Benchmark (surveying); Image (mathematics); Range (aeronautics); Scalability; Artificial intelligence; Decomposition; Computer vision; Database; Geography; Cartography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00154324,0.001607421,0.001186993,0.002319681,0.0008068276,0.002420313,0.003121852,0.001691207,0.009680135],"category_scores_gemma":[0.008228479,0.0007595949,0.001493441,0.001906866,0.001113362,0.005315109,0.002854358,0.002056372,0.009843915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001129451,"about_ca_system_score_gemma":0.001087214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009137458,"about_ca_topic_score_gemma":0.01681696,"domain_scores_codex":[0.9974113,0.0002886854,0.0001157587,0.00112922,0.0008382371,0.0002167428],"domain_scores_gemma":[0.9963069,0.0004828484,0.0001717777,0.002100378,0.0007691438,0.0001690504],"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":[0.001016188,0.000471186,0.006649091,0.001076969,0.0002677068,0.0003902136,0.0003132627,0.03252785,0.0375676,0.01946555,0.2603642,0.6398902],"study_design_scores_gemma":[0.000214406,0.0004282368,0.01623696,0.0003486325,0.0001092279,0.002097451,0.0008410552,0.5110569,0.08269567,0.07280278,0.3129013,0.0002673036],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05975595,0.002723885,0.7427607,0.001027941,0.0008715975,0.0007231103,0.08520077,0.08076131,0.02617481],"genre_scores_gemma":[0.1746565,0.0008522814,0.6350502,0.0007308855,0.0001624484,0.0005060245,0.1752397,0.004802631,0.0079992],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009680135,"threshold_uncertainty_score":0.03238326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01402126733871252,"score_gpt":0.2513516611424488,"score_spread":0.2373303938037363,"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."}}