{"id":"W2562572410","doi":"10.1109/tcsvt.2017.2751589","title":"Object Shape Approximation and Contour Adaptive Depth Image Coding for Virtual View Synthesis","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems for Video Technology","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"View synthesis; Computer vision; Artificial intelligence; Computer science; Codec; Coding (social sciences); Rendering (computer graphics); Image-based modeling and rendering; Depth map; Mathematics; Image (mathematics)","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":[0.0003359668,0.0001882856,0.0003661143,0.0002793587,0.001203027,0.0003302855,0.0004065235,0.0001323741,0.000001222634],"category_scores_gemma":[0.0001008611,0.0001724761,0.00007263415,0.0000941858,0.0001750932,0.0007739048,0.000007797757,0.0001390024,0.000002604421],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004346736,"about_ca_system_score_gemma":0.00003158301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001775053,"about_ca_topic_score_gemma":0.00001790419,"domain_scores_codex":[0.9987668,0.00002953416,0.0002910549,0.0005149861,0.0001078493,0.000289754],"domain_scores_gemma":[0.9986931,0.0003633325,0.000230104,0.0004947831,0.0001491066,0.000069544],"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":[0.00001692015,0.00003834613,0.000009492248,0.0001282077,0.00004794259,0.000002345161,0.0001340152,0.00003264213,0.009115311,0.0311932,0.00003752984,0.9592441],"study_design_scores_gemma":[0.001751624,0.000746497,0.0001176015,0.0006038776,0.0000783564,0.0001598131,0.0008553893,0.951697,0.03610267,0.004790594,0.00256932,0.0005272592],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002172045,0.0003578362,0.9949869,0.0005561925,0.0005285464,0.0009909049,0.0000414689,0.0002326181,0.0001334702],"genre_scores_gemma":[0.9888124,0.0001539107,0.01023848,0.00005450762,0.00002692168,0.0006220281,4.052733e-7,0.00001891438,0.00007247256],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9866403,"threshold_uncertainty_score":0.9252833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04019376285125252,"score_gpt":0.2913771003731263,"score_spread":0.2511833375218738,"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."}}