{"id":"W3003291777","doi":"10.1145/3368313","title":"Adaptive Incident Radiance Field Sampling and Reconstruction Using Deep Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Natural Science Foundation of China","keywords":"Radiance; Path tracing; Computer science; Rendering (computer graphics); Adaptive sampling; Sampling (signal processing); Reinforcement learning; Convolutional neural network; Global illumination; Algorithm; Ray tracing (physics); Importance sampling; Monte Carlo method; Artificial intelligence; Deep learning; Computer vision; Mathematics; Statistics; Optics; Filter (signal processing); Physics","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":[0.0001311129,0.0001402257,0.0001348845,0.0002257926,0.0003941085,0.0001424329,0.000337922,0.00008332019,0.000008334084],"category_scores_gemma":[0.00003614694,0.0001556524,0.00007428362,0.0007343577,0.00004175836,0.0004124654,0.00003147782,0.0003396568,0.00000108995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002351579,"about_ca_system_score_gemma":0.00003018747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005086559,"about_ca_topic_score_gemma":0.00001497519,"domain_scores_codex":[0.998995,0.00005447352,0.000242185,0.000353631,0.0001899912,0.0001647152],"domain_scores_gemma":[0.9992531,0.0001486425,0.0001050285,0.0002799073,0.00008909599,0.0001242201],"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":[0.00008936325,0.0001003009,0.00321391,0.00009864373,0.0001934507,0.00001366545,0.006739532,0.08678149,0.0009939086,0.3385379,0.00003671518,0.5632011],"study_design_scores_gemma":[0.000186094,0.0003928351,0.0002694616,0.00005305899,0.00001384774,0.00002295338,0.00007305294,0.9887818,0.003003685,0.006662744,0.0003379389,0.0002025904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006261793,0.0000778812,0.9921021,0.0009585026,0.0001523039,0.0001521209,4.355319e-7,0.0002704518,0.00002442942],"genre_scores_gemma":[0.9218136,0.0005180907,0.0757837,0.001829056,0.00003163224,0.00001063503,8.932002e-7,0.000009866002,0.000002543181],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9163184,"threshold_uncertainty_score":0.6347321,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05982798003170128,"score_gpt":0.2962870117647453,"score_spread":0.236459031733044,"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."}}