{"id":"W4413146660","doi":"10.1109/cvpr52734.2025.00557","title":"3D-GSW: 3D Gaussian Splatting for Robust Watermarking","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Research Foundation of Korea","keywords":"Computer science; Digital watermarking; Artificial intelligence; Computer vision; Gaussian; Computer graphics (images); Image (mathematics); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003489452,0.0001768539,0.0001829397,0.0002671944,0.0003531499,0.0003393162,0.0008927041,0.00008843181,0.000005344748],"category_scores_gemma":[0.00002553156,0.0001452248,0.0001099877,0.0004253444,0.00004092208,0.0008842291,0.0003413248,0.0001290488,0.000002834156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003059197,"about_ca_system_score_gemma":0.00003031654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001139466,"about_ca_topic_score_gemma":0.000006049501,"domain_scores_codex":[0.9986943,0.00003135133,0.0002746853,0.000447287,0.0001212252,0.0004311716],"domain_scores_gemma":[0.9991421,0.0001266902,0.0000690554,0.0005381429,0.00007377008,0.00005020421],"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":[0.00003348908,0.00008204801,0.004125527,0.0002081986,0.00007630442,0.00002151396,0.000520792,0.0004477768,0.002227707,0.3505874,0.005186831,0.6364825],"study_design_scores_gemma":[0.001442302,0.0002020097,0.002480641,0.0007761467,0.00004975943,0.00003602654,0.0000697042,0.4690512,0.1221347,0.1727065,0.2296857,0.00136531],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004407915,0.00005784133,0.9633501,0.0009362955,0.0003855985,0.0002879428,0.000001446323,0.0009540236,0.03358602],"genre_scores_gemma":[0.1891537,0.00001214464,0.8082833,0.0008655384,0.00005179516,0.00006367471,0.000003788314,0.000009115462,0.001556986],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6351171,"threshold_uncertainty_score":0.5922095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01749855711589366,"score_gpt":0.2664665762332076,"score_spread":0.248968019117314,"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."}}