{"id":"W3034419329","doi":"10.1109/cvpr42600.2020.00753","title":"Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":381,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Inpainting; Computer science; Residual; Artificial intelligence; Convolutional neural network; Inference; Image (mathematics); Computer vision; Deep learning; Image resolution; Pattern recognition (psychology); Algorithm","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002263568,0.0001106692,0.0001206183,0.00004314739,0.0001507207,0.0001958215,0.0004892558,0.0000452787,0.00000556926],"category_scores_gemma":[0.0007430963,0.0001066298,0.00003401979,0.0002330835,0.00005141657,0.001400256,0.000106462,0.00009508207,0.00001490312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003416093,"about_ca_system_score_gemma":0.00003967659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000136897,"about_ca_topic_score_gemma":0.000002269833,"domain_scores_codex":[0.9989861,0.00003273038,0.0002203182,0.0003702604,0.0001647803,0.0002258092],"domain_scores_gemma":[0.9992856,0.0001308893,0.0001192736,0.0001984927,0.0001972947,0.00006842993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000563373,0.00005094439,0.0000670789,0.0001198981,0.00001482281,0.000007729169,0.001693021,0.0000527271,0.5015894,0.2202557,0.01956072,0.2565317],"study_design_scores_gemma":[0.0006243296,0.0002624528,0.0000885915,0.00004448559,0.000006166087,0.000006033478,0.00008050445,0.3810536,0.5736465,0.04136652,0.002501243,0.0003195857],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007351018,0.00004113362,0.9891796,0.007697964,0.00005031126,0.0002524389,0.000002788338,0.001358082,0.0006825859],"genre_scores_gemma":[0.2880342,0.000002494385,0.710529,0.001236394,0.0001013054,0.00002808502,0.000005627708,0.000009011765,0.00005393742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3810009,"threshold_uncertainty_score":0.4348237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02448109100870257,"score_gpt":0.2774175768975865,"score_spread":0.252936485888884,"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."}}