{"id":"W4386260373","doi":"10.1109/crv60082.2023.00010","title":"Towards Low-Cost Learning-based Camera ISP via Unrolled Optimization","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Pipeline (software); Overhead (engineering); Convolutional neural network; Artificial intelligence; Computation; Deep learning; Pipeline transport; Image (mathematics); Optimization problem; Computer engineering; Computer vision; Algorithm; Engineering","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":[0.000279541,0.0001526491,0.0001550125,0.0002362168,0.0001874068,0.0001997244,0.0006908248,0.00006305789,0.00006358464],"category_scores_gemma":[0.000188439,0.000140767,0.00005089851,0.001393268,0.00004517376,0.000663982,0.0002307074,0.0001762651,0.0001546855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006076022,"about_ca_system_score_gemma":0.0001266622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001780011,"about_ca_topic_score_gemma":0.000001669463,"domain_scores_codex":[0.9987317,0.00005776888,0.0002021075,0.0004098153,0.0002852701,0.0003133423],"domain_scores_gemma":[0.9991774,0.00006404267,0.00009525508,0.0004069202,0.0001799574,0.00007643637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001673221,0.00007037514,0.0002134566,0.00004738809,0.000009815511,0.00003934293,0.0002561498,0.8202376,0.002845592,0.00104587,0.003744015,0.1714736],"study_design_scores_gemma":[0.0002717686,0.00003818859,0.00005405231,0.00002104857,0.000002020347,0.000002253878,0.000006034604,0.9786588,0.01802859,0.001550464,0.001182726,0.00018406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000735514,0.00001465436,0.9908225,0.001563022,0.000106432,0.0002044066,4.22297e-7,0.004876302,0.002338727],"genre_scores_gemma":[0.08364841,0.00001303857,0.9138913,0.0007590101,0.00002825321,0.00007116383,0.00001607331,0.00002415814,0.00154858],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1712896,"threshold_uncertainty_score":0.5740312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01249611407470727,"score_gpt":0.2792035035145519,"score_spread":0.2667073894398446,"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."}}