{"id":"W4385534306","doi":"10.1145/3588432.3591512","title":"Parameter-space ReSTIR for Differentiable and Inverse Rendering","year":2023,"lang":"en","type":"article","venue":"","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; University of California, San Diego; Universities Space Research Association; National Science Foundation","keywords":"Rendering (computer graphics); Hessian matrix; Computer science; Differentiable function; Gradient descent; Pixel; Algorithm; Estimator; Computation; Inverse problem; Global illumination; Variance reduction; Mathematical optimization; Resampling; Applied mathematics; Monte Carlo method; Mathematics; Artificial intelligence; Artificial neural network; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001428889,0.00006839314,0.00007883042,0.0001568378,0.00009258091,0.0001786097,0.0002246339,0.00002921521,0.000002041073],"category_scores_gemma":[0.00002736817,0.00006189353,0.00002797507,0.0004250407,0.00001628845,0.0001724153,0.0002871246,0.00002925643,0.000002719622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004710332,"about_ca_system_score_gemma":0.000009272826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001523091,"about_ca_topic_score_gemma":0.000009906506,"domain_scores_codex":[0.9994248,0.00001305352,0.00009385215,0.000237208,0.00007849422,0.0001525517],"domain_scores_gemma":[0.9995229,0.0001254874,0.00002593614,0.0002389732,0.00003437642,0.00005235303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001106455,0.00001053333,0.0008491693,0.00002713678,0.000007037374,0.000001267705,0.0001986241,0.000006187662,0.0002953564,0.9694086,0.02238238,0.006812632],"study_design_scores_gemma":[0.0001332998,0.00006570446,0.001157065,0.00001279721,0.000001769939,0.000001597466,0.00001072744,0.9051033,0.004139143,0.07815931,0.01110509,0.0001102311],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03079975,0.00001079196,0.9674874,0.0004061814,0.00008314396,0.0001318429,8.023197e-7,0.00089008,0.0001900349],"genre_scores_gemma":[0.7079064,0.0001810715,0.2884522,0.0004650402,0.00004809252,0.00009822,0.000009089159,0.00001902842,0.002820922],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9050971,"threshold_uncertainty_score":0.2523945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04759543090597394,"score_gpt":0.3056790960278946,"score_spread":0.2580836651219207,"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."}}