{"id":"W4409368447","doi":"10.1609/aaai.v39i4.32420","title":"PixelMan: Consistent Object Editing with Diffusion Models via Pixel Manipulation and Generation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Huawei Technologies (Canada)","funders":"","keywords":"Object (grammar); Computer science; Diffusion; Pixel; Image editing; Computer graphics (images); Artificial intelligence; Computer vision; Physics; Image (mathematics)","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":[0.00137611,0.001231101,0.001140753,0.0007449214,0.0004712276,0.001355015,0.003535243,0.001716867,0.002496926],"category_scores_gemma":[0.003886907,0.0008119631,0.001269651,0.0005773159,0.001038064,0.001945213,0.001789531,0.002247151,0.001114776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008084668,"about_ca_system_score_gemma":0.001003827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004210259,"about_ca_topic_score_gemma":0.006391954,"domain_scores_codex":[0.9993057,0.0001249734,0.00003035729,0.0002255383,0.0002641917,0.00004911514],"domain_scores_gemma":[0.9985263,0.0006586509,0.0001448514,0.0004361241,0.0001713425,0.00006273863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002706267,0.0001287264,0.0009385145,0.0003039507,0.0001738963,0.0002026311,0.0002822076,0.4285074,0.04033503,0.02116572,0.007937812,0.4997534],"study_design_scores_gemma":[0.00002142452,0.00003492132,0.00007592147,0.000009361375,0.00001260492,0.00009092184,0.00001170358,0.9812553,0.009327134,0.006361973,0.002784369,0.00001445404],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003383653,0.000210776,0.993306,0.00007375381,0.00004226754,0.00003615527,0.00004236023,0.002203421,0.000701657],"genre_scores_gemma":[0.122825,0.0003071747,0.8707294,0.0003241699,0.00007026817,0.0001311516,0.0004124942,0.001081238,0.004119022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004210259,"threshold_uncertainty_score":0.008371532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05856749182720886,"score_gpt":0.2501098546228132,"score_spread":0.1915423627956043,"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."}}