{"id":"W4392903561","doi":"10.1109/icassp48485.2024.10448413","title":"Capturing Detail Variations for Lightweight Neural Radiance Fields","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Radiance; Computer science; Rendering (computer graphics); Convolutional neural network; Grid; Voxel; Computation; Artificial neural network; Artificial intelligence; Visualization; Computer graphics (images); Computer vision; Algorithm; Remote sensing","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":[0.0004609806,0.000924682,0.0005365967,0.0005202898,0.0001930638,0.0005224489,0.0009588448,0.0006100935,0.002225467],"category_scores_gemma":[0.001406054,0.0004391286,0.000713538,0.000443874,0.0004027435,0.001149817,0.0006472909,0.001294693,0.0005641483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005048119,"about_ca_system_score_gemma":0.0004902672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004533837,"about_ca_topic_score_gemma":0.008294473,"domain_scores_codex":[0.9998542,0.00002863887,0.000005500419,0.00004210496,0.00004895457,0.00002052961],"domain_scores_gemma":[0.9997408,0.0001003177,0.00003223279,0.0000632615,0.0000452081,0.00001826806],"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":[0.0001426401,0.00007145127,0.001181256,0.0001109356,0.0000602392,0.00009657939,0.00007496717,0.664616,0.03801578,0.007845749,0.004313462,0.2834708],"study_design_scores_gemma":[0.000006023994,0.00001371603,0.0001742275,0.000004780812,0.000005068094,0.00003695046,0.000005560678,0.9937636,0.002921875,0.002145941,0.0009160336,0.000006271746],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02844421,0.0002490746,0.9677537,0.000131024,0.00003875337,0.00002727116,0.0001961355,0.001795892,0.00136402],"genre_scores_gemma":[0.5372094,0.0004717003,0.4558589,0.0002552107,0.00006950526,0.0000831061,0.001204835,0.0006638253,0.004183689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004533837,"threshold_uncertainty_score":0.009014904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01762670423470435,"score_gpt":0.281518891797803,"score_spread":0.2638921875630987,"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."}}