{"id":"W4414603838","doi":"10.1109/tvcg.2025.3615421","title":"SeG-Gaussian:Segmentation-Guided 3D Gaussian Optimization for Novel View Synthesis","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Beijing Municipal Science and Technology Commission; National Natural Science Foundation of China","keywords":"Leverage (statistics); Gaussian; Outlier; View synthesis; Segmentation; Redundancy (engineering); Radiance; Mixture model; Regularization (linguistics)","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"],"consensus_categories":[],"category_scores_codex":[0.000115443,0.0002372423,0.0002262814,0.000487305,0.0003123552,0.0001478914,0.00008604529,0.0001570395,0.0000286821],"category_scores_gemma":[0.00000462185,0.0002550279,0.00009087749,0.0007292955,0.00004341988,0.0001722605,0.000001194146,0.00009136133,0.000001786651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005165434,"about_ca_system_score_gemma":0.00002859616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006525506,"about_ca_topic_score_gemma":0.00001219557,"domain_scores_codex":[0.9989114,0.00003949683,0.0004118549,0.0002854906,0.0001578456,0.000193862],"domain_scores_gemma":[0.9994019,0.0001399687,0.00005333783,0.0001834189,0.0001444609,0.00007689992],"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":[0.00001296165,0.0001132302,0.00001234974,0.0002374946,0.0001006574,2.640262e-7,0.0001247279,0.9294303,0.0000739048,0.06205001,0.0003834656,0.007460644],"study_design_scores_gemma":[0.0006595417,0.00004974852,0.00004362291,0.000154521,0.0001152652,0.000002389549,0.00002691191,0.9935802,0.004192287,0.0001057038,0.0008232535,0.0002466056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004784609,0.00005978293,0.9975066,0.0000844971,0.0008463828,0.0005224094,0.00004395082,0.0003289839,0.000128997],"genre_scores_gemma":[0.944075,0.001985346,0.05107149,0.001829862,0.0001343273,0.000361315,0.0002193918,0.0001334519,0.0001897743],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.946435,"threshold_uncertainty_score":0.9999902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01964597975044092,"score_gpt":0.2691828605018178,"score_spread":0.2495368807513769,"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."}}