{"id":"W4391953425","doi":"10.1109/tetci.2024.3359038","title":"MuralDiff: Diffusion for Ancient Murals Restoration on Large-Scale Pre-Training","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Emerging Topics in Computational Intelligence","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Training (meteorology); Scale (ratio); Diffusion; Visual arts; Art; Geography; Cartography; Physics","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":[0.0003762477,0.0001696526,0.0001411289,0.0004287337,0.0003324784,0.0002510085,0.0002892129,0.00008278599,0.0000147111],"category_scores_gemma":[0.00001694726,0.0001675039,0.0001003974,0.0005997554,0.00004705288,0.0004875166,0.000004132469,0.0003082984,0.00002052622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001484857,"about_ca_system_score_gemma":0.000151451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009489289,"about_ca_topic_score_gemma":0.00003079526,"domain_scores_codex":[0.9984148,0.00005468849,0.0003934496,0.0005256922,0.0003317424,0.0002796469],"domain_scores_gemma":[0.9992323,0.0003340306,0.00006093116,0.0001937197,0.0001231019,0.00005593215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001495668,0.00009643992,0.000005584432,0.00005614804,0.000008250729,0.000003564615,0.003257871,0.6185387,0.0001582174,0.01160431,0.00009110916,0.3661648],"study_design_scores_gemma":[0.0001017749,0.0001156445,0.0000921247,0.0003049811,0.00000550525,0.00001611774,0.0001791769,0.9691955,0.00438064,0.02391561,0.001507902,0.0001850176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01869648,0.00009963412,0.9755217,0.001747711,0.003285443,0.0002422191,0.00001385894,0.0002481167,0.0001447693],"genre_scores_gemma":[0.8926372,0.00002554355,0.1063521,0.0002745486,0.0001314185,0.00007677142,0.000008265935,0.00001388563,0.0004803269],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8739407,"threshold_uncertainty_score":0.6830611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03954619080813793,"score_gpt":0.328253793318908,"score_spread":0.2887076025107701,"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."}}