{"id":"W4294959213","doi":"10.1145/3550469.3555392","title":"CLIP-Mesh: Generating textured meshes from text using pretrained image-text models","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":183,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Polygon mesh; Computer science; Embedding; Image (mathematics); Limit (mathematics); Artificial intelligence; Surface (topology); Generative model; Texture (cosmology); Computer vision; Pattern recognition (psychology); Generative grammar; Computer graphics (images); Mathematics; Geometry","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.000666957,0.0006540079,0.0006999302,0.0005242201,0.0005229427,0.001814683,0.003246364,0.0003764384,0.0004795912],"category_scores_gemma":[0.00003605353,0.000665749,0.0004205887,0.0007115997,0.00007402118,0.0007646755,0.008515239,0.0009858663,0.000004577403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001688872,"about_ca_system_score_gemma":0.0004042243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001066449,"about_ca_topic_score_gemma":0.00003006077,"domain_scores_codex":[0.9955047,0.0003716068,0.000947673,0.001791807,0.0008616234,0.0005226114],"domain_scores_gemma":[0.9966548,0.0001727251,0.0005592449,0.002115271,0.0003121897,0.0001857541],"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":[0.00001324822,0.0003656122,0.0001664624,0.0001787058,0.0003876259,0.00006807923,0.005318111,0.03833411,0.006511551,0.8986803,0.01252677,0.03744943],"study_design_scores_gemma":[0.0001698178,0.00003975382,0.00003060228,0.00007451745,0.00002430731,0.000004813834,0.00003160907,0.8765232,0.001997301,0.1196247,0.0007770764,0.000702277],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00599027,0.0005607847,0.9865021,0.0002130191,0.00118659,0.0007087229,0.00008940896,0.001710198,0.00303887],"genre_scores_gemma":[0.2026668,0.0001651094,0.7948948,0.001047985,0.0004358038,0.0001257837,0.0002231343,0.00008193709,0.0003586366],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8381891,"threshold_uncertainty_score":0.9995794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05548151210045593,"score_gpt":0.3192066341915963,"score_spread":0.2637251220911404,"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."}}