{"paper":{"title":"OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"OpenGaFF models semantics as a continuous function of 3D Gaussian geometry to achieve spatially coherent open-vocabulary scene understanding.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Federico Tombari, Kunyi Li, Michael Niemeyer, Nassir Navab, Sen Wang, Stefano Gasperini","submitted_at":"2026-05-07T12:10:07Z","abstract_excerpt":"Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semantic predictions across multi-view observations. In this paper, we present OpenGaFF, a novel framework for open-vocabulary 3D scene understanding built upon 3D Gaussian Splatting. At the core of our method is a Gaussian Feature Field that models semantics as a continuous function of Gaussian geometry and appearance. By explicitly conditioning semantic predictions on geometric structure, this formulation strengthens the coupling between geometry and se"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments on standard 2D and 3D open-vocabulary benchmarks demonstrate that our method consistently outperforms prior approaches, achieving improved segmentation quality, stronger 3D semantic consistency and a semantically interpretable codebook that provides insight into the learned representation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That explicitly conditioning semantic predictions on geometric structure will strengthen the coupling between geometry and semantics and thereby improve spatial coherence across similar structures in 3D space.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OpenGaFF combines a geometry-conditioned Gaussian Feature Field with codebook-guided attention to deliver more spatially coherent open-vocabulary 3D semantic segmentation than prior methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"OpenGaFF models semantics as a continuous function of 3D Gaussian geometry to achieve spatially coherent open-vocabulary scene understanding.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"42e8632cbe2ccd49b0f2ea1ae14a441ab86887ccc7f5e90d3b0f1e442814b536"},"source":{"id":"2605.06088","kind":"arxiv","version":2},"verdict":{"id":"3967e812-c76a-4ab8-8f02-1c839b5a92eb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T14:04:10.168160Z","strongest_claim":"Extensive experiments on standard 2D and 3D open-vocabulary benchmarks demonstrate that our method consistently outperforms prior approaches, achieving improved segmentation quality, stronger 3D semantic consistency and a semantically interpretable codebook that provides insight into the learned representation.","one_line_summary":"OpenGaFF combines a geometry-conditioned Gaussian Feature Field with codebook-guided attention to deliver more spatially coherent open-vocabulary 3D semantic segmentation than prior methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That explicitly conditioning semantic predictions on geometric structure will strengthen the coupling between geometry and semantics and thereby improve spatial coherence across similar structures in 3D space.","pith_extraction_headline":"OpenGaFF models semantics as a continuous function of 3D Gaussian geometry to achieve spatially coherent open-vocabulary scene understanding."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.06088/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T19:01:19.520813Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:57:10.665678Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6e1d78a92112d4200ae20b500cbc1d24fa40b8741aff3383b0a0b39fbcaa6717"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}