{"paper":{"title":"Semantic Foam: Unifying Spatial and Semantic Scene Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Semantic Foam attaches semantic features to Voronoi cells for consistent object segmentation in reconstructed scenes.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amr Sharafeldin, Andrea Tagliasacchi, Aryan Mikaeili, Daniel Rebain, Kwang Moo Yi, Shrisudhan Govindarajan, Thomas Walker","submitted_at":"2026-04-29T03:40:13Z","abstract_excerpt":"Modern scene reconstruction methods, such as 3D Gaussian Splatting, deliver photo-realistic novel view synthesis at real-time speeds, yet their adoption in interactive graphics applications has been limited. A major bottleneck is the difficulty of interacting with these representations compared to traditional, human-authored 3D assets. While previous research has attempted to impose semantic decomposition on these models, significant challenges remain regarding segmentation quality and consistency. To address this, we introduce Semantic Foam, extending the recently proposed Radiant Foam repres"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our approach integrates the natural spatial volumetric decomposition of Radiant Foam's Voronoi mesh with an explicit semantic feature field parameterized at the cell level. This explicit structure enables direct spatial regularization, which prevents artifacts caused by occlusion or inconsistent supervision across views - common pitfalls for other point-based representations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That attaching semantic features to the Voronoi cells of Radiant Foam will preserve rendering quality while delivering consistent segmentation without new artifacts or loss of detail from the underlying spatial decomposition.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Semantic Foam unifies spatial Voronoi decomposition with cell-level semantic features to achieve superior object segmentation by enabling direct spatial regularization that avoids occlusion and view-inconsistency artifacts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Semantic Foam attaches semantic features to Voronoi cells for consistent object segmentation in reconstructed scenes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9ae632426cdee0103f1c5cc8aaeb66067ed4a95ad25a9a34051e86692ab28ea0"},"source":{"id":"2604.26262","kind":"arxiv","version":3},"verdict":{"id":"ea9a95b6-844a-4c28-aac4-699ef73e0672","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T13:37:11.835822Z","strongest_claim":"Our approach integrates the natural spatial volumetric decomposition of Radiant Foam's Voronoi mesh with an explicit semantic feature field parameterized at the cell level. This explicit structure enables direct spatial regularization, which prevents artifacts caused by occlusion or inconsistent supervision across views - common pitfalls for other point-based representations.","one_line_summary":"Semantic Foam unifies spatial Voronoi decomposition with cell-level semantic features to achieve superior object segmentation by enabling direct spatial regularization that avoids occlusion and view-inconsistency artifacts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That attaching semantic features to the Voronoi cells of Radiant Foam will preserve rendering quality while delivering consistent segmentation without new artifacts or loss of detail from the underlying spatial decomposition.","pith_extraction_headline":"Semantic Foam attaches semantic features to Voronoi cells for consistent object segmentation in reconstructed scenes."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.26262/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T00:39:45.566994Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T20:22:51.530879Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7e9b9b98d7745e9db93a63cfa5442d9bf353206ab782755c807422552f31a8ae"},"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"}