{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JYOTDEVF3YSJIFQ37ALK2VSPFT","short_pith_number":"pith:JYOTDEVF","schema_version":"1.0","canonical_sha256":"4e1d3192a5de2494161bf816ad564f2cf3e67cc5b67d7154ae6e116514ba5cf7","source":{"kind":"arxiv","id":"2506.23611","version":1},"attestation_state":"computed","paper":{"title":"AttentionGS: Towards Initialization-Free 3D Gaussian Splatting via Structural Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiangang Li, Yifeng Shi, Zhenjia Li, Ziao Liu","submitted_at":"2025-06-30T08:16:43Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) is a powerful alternative to Neural Radiance Fields (NeRF), excelling in complex scene reconstruction and efficient rendering. However, it relies on high-quality point clouds from Structure-from-Motion (SfM), limiting its applicability. SfM also fails in texture-deficient or constrained-view scenarios, causing severe degradation in 3DGS reconstruction. To address this limitation, we propose AttentionGS, a novel framework that eliminates the dependency on high-quality initial point clouds by leveraging structural attention for direct 3D reconstruction from randomly "},"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":"2506.23611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T08:16:43Z","cross_cats_sorted":[],"title_canon_sha256":"93563d01d5d4d7630a30d10a8a86fe7e9f43dd7442f3a0b3671611d6661354d2","abstract_canon_sha256":"8c7d4b723df1be5788629ae69bc1f3904cea79c930fca9242ea7fcae5a6b677f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:24.843880Z","signature_b64":"4GOHd/q3GxJRkjb/6JVRbrCaNIYnue8Rbf4YNgQ8V7Zz164MBuapbDhEwUWl242mJKaYYqnYz4gbxc+/PXoxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e1d3192a5de2494161bf816ad564f2cf3e67cc5b67d7154ae6e116514ba5cf7","last_reissued_at":"2026-07-05T11:29:24.843367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:24.843367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AttentionGS: Towards Initialization-Free 3D Gaussian Splatting via Structural Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiangang Li, Yifeng Shi, Zhenjia Li, Ziao Liu","submitted_at":"2025-06-30T08:16:43Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) is a powerful alternative to Neural Radiance Fields (NeRF), excelling in complex scene reconstruction and efficient rendering. However, it relies on high-quality point clouds from Structure-from-Motion (SfM), limiting its applicability. SfM also fails in texture-deficient or constrained-view scenarios, causing severe degradation in 3DGS reconstruction. To address this limitation, we propose AttentionGS, a novel framework that eliminates the dependency on high-quality initial point clouds by leveraging structural attention for direct 3D reconstruction from randomly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23611","kind":"arxiv","version":1},"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/2506.23611/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":"2506.23611","created_at":"2026-07-05T11:29:24.843430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23611v1","created_at":"2026-07-05T11:29:24.843430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23611","created_at":"2026-07-05T11:29:24.843430+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYOTDEVF3YSJ","created_at":"2026-07-05T11:29:24.843430+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYOTDEVF3YSJIFQ3","created_at":"2026-07-05T11:29:24.843430+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYOTDEVF","created_at":"2026-07-05T11:29:24.843430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10239","citing_title":"AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10239","citing_title":"AdaptSplat: Adapting Vision Foundation Models for Feed-Forward 3D Gaussian Splatting","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21400","citing_title":"You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JYOTDEVF3YSJIFQ37ALK2VSPFT","json":"https://pith.science/pith/JYOTDEVF3YSJIFQ37ALK2VSPFT.json","graph_json":"https://pith.science/api/pith-number/JYOTDEVF3YSJIFQ37ALK2VSPFT/graph.json","events_json":"https://pith.science/api/pith-number/JYOTDEVF3YSJIFQ37ALK2VSPFT/events.json","paper":"https://pith.science/paper/JYOTDEVF"},"agent_actions":{"view_html":"https://pith.science/pith/JYOTDEVF3YSJIFQ37ALK2VSPFT","download_json":"https://pith.science/pith/JYOTDEVF3YSJIFQ37ALK2VSPFT.json","view_paper":"https://pith.science/paper/JYOTDEVF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23611&json=true","fetch_graph":"https://pith.science/api/pith-number/JYOTDEVF3YSJIFQ37ALK2VSPFT/graph.json","fetch_events":"https://pith.science/api/pith-number/JYOTDEVF3YSJIFQ37ALK2VSPFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYOTDEVF3YSJIFQ37ALK2VSPFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYOTDEVF3YSJIFQ37ALK2VSPFT/action/storage_attestation","attest_author":"https://pith.science/pith/JYOTDEVF3YSJIFQ37ALK2VSPFT/action/author_attestation","sign_citation":"https://pith.science/pith/JYOTDEVF3YSJIFQ37ALK2VSPFT/action/citation_signature","submit_replication":"https://pith.science/pith/JYOTDEVF3YSJIFQ37ALK2VSPFT/action/replication_record"}},"created_at":"2026-07-05T11:29:24.843430+00:00","updated_at":"2026-07-05T11:29:24.843430+00:00"}