{"id":"W4404820184","doi":"10.1007/978-3-031-72848-8_19","title":"VQA-Diff: Exploiting VQA and Diffusion for Zero-Shot Image-to-3D Vehicle Asset Generation in Autonomous Driving","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; York University","funders":"","keywords":"Computer science; Shot (pellet); Zero (linguistics); Asset (computer security); Image (mathematics); Computer vision; Diffusion; Artificial intelligence; Computer security; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004403951,0.0007167715,0.0006334507,0.0007494329,0.0003057232,0.0008846396,0.001531667,0.0009094354,0.004305884],"category_scores_gemma":[0.001088367,0.0004574319,0.0006864043,0.0005455446,0.0003852223,0.0009084594,0.001383604,0.000861723,0.001342426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003985279,"about_ca_system_score_gemma":0.0005830542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004895012,"about_ca_topic_score_gemma":0.006796399,"domain_scores_codex":[0.9998048,0.00002315657,0.000008602804,0.00004725536,0.0000917796,0.00002444548],"domain_scores_gemma":[0.9997135,0.00009486766,0.00001616762,0.00006515744,0.00008847901,0.00002180831],"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":[0.000199086,0.0001123394,0.0007419247,0.0001453242,0.0000820959,0.0001425614,0.0001289846,0.1599413,0.04035529,0.01259296,0.01338014,0.7721779],"study_design_scores_gemma":[0.000009218015,0.00002801675,0.0001773635,0.000007715305,0.000005906071,0.00007319477,0.00001406955,0.9795853,0.009398647,0.007413976,0.003275843,0.00001071609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005572465,0.0002023651,0.9889765,0.00005927034,0.00007918325,0.00004101068,0.0001380173,0.00368172,0.001249402],"genre_scores_gemma":[0.2267424,0.0003236327,0.7649225,0.0001524037,0.00007890478,0.00007008887,0.0009059571,0.001194575,0.005609605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004895012,"threshold_uncertainty_score":0.01440459,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02722686866305506,"score_gpt":0.291987410812122,"score_spread":0.264760542149067,"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."}}