{"id":"W2907097116","doi":"10.48550/arxiv.1901.00212","title":"EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":587,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Inpainting; Hallucinating; Generator (circuit theory); Image (mathematics); Enhanced Data Rates for GSM Evolution; Artificial intelligence; Computer science; Filling-in; Code (set theory); A priori and a posteriori; Generative grammar; Deep learning; Pattern recognition (psychology); Computer vision; Power (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006740167,0.0008969491,0.0006160863,0.0004532441,0.0002200916,0.0006086285,0.001938657,0.001156698,0.003585772],"category_scores_gemma":[0.001811859,0.0004746427,0.0006848703,0.0004031246,0.0007904412,0.0007863052,0.00152999,0.001882026,0.0008862097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005216321,"about_ca_system_score_gemma":0.0003723499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001569287,"about_ca_topic_score_gemma":0.00251178,"domain_scores_codex":[0.9997639,0.00005258967,0.000006991143,0.00006553571,0.00008328568,0.00002767224],"domain_scores_gemma":[0.9995616,0.0002224932,0.00003861522,0.0001092283,0.00004161304,0.00002646095],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001396352,0.0000863609,0.0006200753,0.0001051099,0.00007397689,0.0001507201,0.00007120275,0.8540486,0.0105243,0.01280037,0.007204705,0.114175],"study_design_scores_gemma":[0.000008622483,0.00001867926,0.00005255136,0.000004542707,0.000004128437,0.00004333224,0.000002808782,0.9928154,0.002454354,0.003495326,0.001096052,0.000004269791],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01108968,0.0002649762,0.9837044,0.0001681316,0.00005536002,0.00007339923,0.0001659973,0.002345482,0.002132431],"genre_scores_gemma":[0.5105965,0.0004704043,0.4750168,0.0006344353,0.00009749099,0.0002952619,0.001087023,0.0007971721,0.01100497],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003585772,"threshold_uncertainty_score":0.01199567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03475309409311431,"score_gpt":0.1705201107510971,"score_spread":0.1357670166579828,"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."}}