{"paper":{"title":"DVD: Discrete Voxel Diffusion for 3D Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Treating voxel occupancy as discrete categories in diffusion yields a direct framework for 3D voxel generation, uncertainty estimation, and editing.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fupeng Sun, Heliang Zheng, Jiaqi Wu, Yingzhen Li, Zhengrui Xiang","submitted_at":"2026-05-08T16:32:17Z","abstract_excerpt":"We introduce Discrete Voxel Diffusion (DVD), a discrete diffusion framework to generate, assess, and edit sparse voxels for SLat (Structured LATent) based 3D generative pipelines. Although discrete diffusion has not generally displaced continuous diffusion in image-like generation, we show that it can be an effective first-stage prior for sparse voxel scaffolds. By treating voxel occupancy as a native discrete variable, DVD avoids continuous-to-discrete thresholding and provides a simple framework for voxel generation, uncertainty estimation, and editing. Beyond quality gains, DVD provides mor"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By treating voxel occupancy as a native discrete variable, DVD avoids continuous-to-discrete thresholding and provides a simple framework for voxel generation, uncertainty estimation, and editing.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That modeling voxel occupancy directly as a discrete categorical variable yields an effective first-stage prior for sparse voxel scaffolds in SLat-based 3D pipelines without requiring continuous representations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DVD treats voxel occupancy as a discrete variable in a diffusion framework to generate, assess, and edit sparse 3D voxels without continuous thresholding.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Treating voxel occupancy as discrete categories in diffusion yields a direct framework for 3D voxel generation, uncertainty estimation, and editing.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fe114600bce7f47757c24ff74dd71bc908464b243c1583cfc6d0fba2a715bf9e"},"source":{"id":"2605.07971","kind":"arxiv","version":2},"verdict":{"id":"cecac77d-781c-4b01-a27a-025e1f4eefe9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T03:13:19.201837Z","strongest_claim":"By treating voxel occupancy as a native discrete variable, DVD avoids continuous-to-discrete thresholding and provides a simple framework for voxel generation, uncertainty estimation, and editing.","one_line_summary":"DVD treats voxel occupancy as a discrete variable in a diffusion framework to generate, assess, and edit sparse 3D voxels without continuous thresholding.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That modeling voxel occupancy directly as a discrete categorical variable yields an effective first-stage prior for sparse voxel scaffolds in SLat-based 3D pipelines without requiring continuous representations.","pith_extraction_headline":"Treating voxel occupancy as discrete categories in diffusion yields a direct framework for 3D voxel generation, uncertainty estimation, and editing."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07971/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T10:02:09.228684Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T04:44:52.428639Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T15:31:18.057760Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:20:59.864781Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"042d5a77075aad7b598bdbed94a1f3f6f1bf84cf5f9c2ae38a339a279340bd23"},"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"}