{"id":"W2972324374","doi":"10.1109/iccvw.2019.00409","title":"Edge-Informed Single Image Super-Resolution","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Inpainting; Artificial intelligence; Computer science; Computer vision; Interpolation (computer graphics); Image (mathematics); Image texture; Code (set theory); Pyramid (geometry); Pattern recognition (psychology); Image processing; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002313901,0.0003809586,0.0003680114,0.0002443004,0.00009701165,0.0007357254,0.00256132,0.0003134337,0.00004492886],"category_scores_gemma":[0.0002201164,0.0003583747,0.0001474937,0.0002349408,0.0001040967,0.001605605,0.004675003,0.0006374484,0.0003407421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003617475,"about_ca_system_score_gemma":0.0005085086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003496187,"about_ca_topic_score_gemma":0.000006679319,"domain_scores_codex":[0.9977586,0.00003905723,0.0004205543,0.0008793044,0.0004163132,0.0004861429],"domain_scores_gemma":[0.997315,0.00008761223,0.0002440253,0.00191167,0.0003445554,0.00009708555],"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":[0.00006135444,0.001201147,0.0003023059,0.003918129,0.0001750706,0.0001223199,0.003648876,0.001268553,0.1848527,0.07454359,0.2775513,0.4523546],"study_design_scores_gemma":[0.0004616655,0.0002109407,0.0001633632,0.0007483332,0.00002363124,0.00005497053,0.00003206778,0.6449882,0.1358088,0.1749752,0.0406594,0.001873333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001177852,0.0002503339,0.9376785,0.0009685262,0.0008588544,0.0004434414,0.000004673594,0.002793885,0.05688407],"genre_scores_gemma":[0.02003851,0.00004307453,0.975328,0.0004752472,0.0001078262,0.00006146455,0.00002668832,0.00003258306,0.003886554],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6437197,"threshold_uncertainty_score":0.9998868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02787805075911091,"score_gpt":0.3017293662611376,"score_spread":0.2738513155020266,"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."}}