{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4NLAZEHLOLUVE7CDLVRKOWI6MQ","short_pith_number":"pith:4NLAZEHL","schema_version":"1.0","canonical_sha256":"e3560c90eb72e9527c435d62a7591e641e3160c02139eec5ee996dad7eec81a6","source":{"kind":"arxiv","id":"2509.19297","version":3},"attestation_state":"computed","paper":{"title":"VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Donny Y. Chen, Feng Chen, Haoxiao Wang, Hengyu Liu, Jia-Wang Bian, Weijie Wang, Wenkang Qin, Yeqing Chen, Zeyu Zhang, Zheng Zhu, Zhiyuan Feng","submitted_at":"2025-09-23T17:59:02Z","abstract_excerpt":"Feed-forward 3D Gaussian Splatting (3DGS) has emerged as a highly effective solution for novel view synthesis. Existing methods predominantly rely on a \\emph{pixel-aligned} Gaussian prediction paradigm, where each 2D pixel is mapped to a 3D Gaussian. We rethink this widely adopted formulation and identify several inherent limitations: it renders the reconstructed 3D models heavily dependent on the number of input views, leads to view-biased density distributions, and introduces alignment errors, particularly when source views contain occlusions or low texture. To address these challenges, we i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.19297","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-23T17:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"547a9db8aac350ec37d2802f78a226d4cd02d2206e94f5bcabe1979529bddd28","abstract_canon_sha256":"ad1b6c34c59b0c53b501ba890630a04f257817a2fa2b7e170d525a68c2e352f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:17:46.226936Z","signature_b64":"zxBxhZ55hm3LIH1EYYOimAj1/iTupi6LDn3j/h7CPzn9HwxlWhSmCcD4BVRnMxcdTitkAnEWAlc11KOuWa1oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3560c90eb72e9527c435d62a7591e641e3160c02139eec5ee996dad7eec81a6","last_reissued_at":"2026-06-25T01:17:46.226440Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:17:46.226440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Donny Y. Chen, Feng Chen, Haoxiao Wang, Hengyu Liu, Jia-Wang Bian, Weijie Wang, Wenkang Qin, Yeqing Chen, Zeyu Zhang, Zheng Zhu, Zhiyuan Feng","submitted_at":"2025-09-23T17:59:02Z","abstract_excerpt":"Feed-forward 3D Gaussian Splatting (3DGS) has emerged as a highly effective solution for novel view synthesis. Existing methods predominantly rely on a \\emph{pixel-aligned} Gaussian prediction paradigm, where each 2D pixel is mapped to a 3D Gaussian. We rethink this widely adopted formulation and identify several inherent limitations: it renders the reconstructed 3D models heavily dependent on the number of input views, leads to view-biased density distributions, and introduces alignment errors, particularly when source views contain occlusions or low texture. To address these challenges, we i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.19297","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.19297/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.19297","created_at":"2026-06-25T01:17:46.226499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.19297v3","created_at":"2026-06-25T01:17:46.226499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.19297","created_at":"2026-06-25T01:17:46.226499+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NLAZEHLOLUV","created_at":"2026-06-25T01:17:46.226499+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NLAZEHLOLUVE7CD","created_at":"2026-06-25T01:17:46.226499+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NLAZEHL","created_at":"2026-06-25T01:17:46.226499+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":15,"sample":[{"citing_arxiv_id":"2605.07287","citing_title":"SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20155","citing_title":"GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10239","citing_title":"AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15760","citing_title":"Learn2Splat: Extending the Horizon of Learned 3DGS Optimization","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2512.04021","citing_title":"C3G: Learning Compact 3D Representations with 2K Gaussians","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03359","citing_title":"Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26454","citing_title":"Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10239","citing_title":"AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20155","citing_title":"GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07287","citing_title":"SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07053","citing_title":"AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04874","citing_title":"Free-Range Gaussians: Non-Grid-Aligned Generative 3D Gaussian Reconstruction","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14025","citing_title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","ref_index":118,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15284","citing_title":"GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17472","citing_title":"UniMesh: Unifying 3D Mesh Understanding and Generation","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NLAZEHLOLUVE7CDLVRKOWI6MQ","json":"https://pith.science/pith/4NLAZEHLOLUVE7CDLVRKOWI6MQ.json","graph_json":"https://pith.science/api/pith-number/4NLAZEHLOLUVE7CDLVRKOWI6MQ/graph.json","events_json":"https://pith.science/api/pith-number/4NLAZEHLOLUVE7CDLVRKOWI6MQ/events.json","paper":"https://pith.science/paper/4NLAZEHL"},"agent_actions":{"view_html":"https://pith.science/pith/4NLAZEHLOLUVE7CDLVRKOWI6MQ","download_json":"https://pith.science/pith/4NLAZEHLOLUVE7CDLVRKOWI6MQ.json","view_paper":"https://pith.science/paper/4NLAZEHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.19297&json=true","fetch_graph":"https://pith.science/api/pith-number/4NLAZEHLOLUVE7CDLVRKOWI6MQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4NLAZEHLOLUVE7CDLVRKOWI6MQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NLAZEHLOLUVE7CDLVRKOWI6MQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NLAZEHLOLUVE7CDLVRKOWI6MQ/action/storage_attestation","attest_author":"https://pith.science/pith/4NLAZEHLOLUVE7CDLVRKOWI6MQ/action/author_attestation","sign_citation":"https://pith.science/pith/4NLAZEHLOLUVE7CDLVRKOWI6MQ/action/citation_signature","submit_replication":"https://pith.science/pith/4NLAZEHLOLUVE7CDLVRKOWI6MQ/action/replication_record"}},"created_at":"2026-06-25T01:17:46.226499+00:00","updated_at":"2026-06-25T01:17:46.226499+00:00"}