{"id":"W4386065379","doi":"10.1109/cvpr52729.2023.01980","title":"SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; York University; University of Toronto","funders":"","keywords":"Inpainting; Artificial intelligence; Computer science; Computer vision; Segmentation; Benchmark (surveying); Task (project management); Set (abstract data type); Object (grammar); Consistency (knowledge bases); Image segmentation; Context (archaeology); Pattern recognition (psychology); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006482719,0.0009710671,0.0008726969,0.000722522,0.0002279909,0.0008294165,0.001615592,0.001269365,0.002760984],"category_scores_gemma":[0.001359357,0.0004337758,0.0008115863,0.0004169754,0.0005547556,0.001067602,0.001016429,0.0012783,0.0006860131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005551722,"about_ca_system_score_gemma":0.0004873798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001709213,"about_ca_topic_score_gemma":0.002819434,"domain_scores_codex":[0.9997395,0.00003794647,0.00001036212,0.00007878921,0.0001033768,0.00003014361],"domain_scores_gemma":[0.9996771,0.0001248543,0.00004472529,0.00007779791,0.00004836445,0.00002721661],"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":[0.000280236,0.0001846409,0.0006271371,0.000401936,0.0001343127,0.0002398294,0.0001831839,0.391424,0.07600583,0.01237395,0.00844421,0.5097008],"study_design_scores_gemma":[0.00002285093,0.00007126394,0.0002345391,0.00001713247,0.00001381458,0.0001638677,0.00001458455,0.9800981,0.01166222,0.004726553,0.00295985,0.00001515161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0129677,0.0006772616,0.9818345,0.0001315211,0.00006863898,0.0000617529,0.0001463253,0.002189371,0.001922979],"genre_scores_gemma":[0.2733352,0.0007526128,0.7178131,0.0003862472,0.0001467708,0.0001277058,0.000932847,0.0006553312,0.005850113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002760984,"threshold_uncertainty_score":0.009236395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02110429758561817,"score_gpt":0.3002700869392781,"score_spread":0.27916578935366,"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."}}