{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HRR2Y6WGXD4SXS2H3WFBY54ZED","short_pith_number":"pith:HRR2Y6WG","schema_version":"1.0","canonical_sha256":"3c63ac7ac6b8f92bcb47dd8a1c779920de4b2a5869712b280c9cc6b68ff35608","source":{"kind":"arxiv","id":"2404.07977","version":4},"attestation_state":"computed","paper":{"title":"Gaga: Group Any Gaussians via 3D-aware Memory Bank","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhijit Kundu, Ming-Hsuan Yang, Weijie Lyu, Xueting Li, Yi-Hsuan Tsai","submitted_at":"2024-04-11T17:57:19Z","abstract_excerpt":"We introduce Gaga, a framework that reconstructs and segments open-world 3D scenes by leveraging inconsistent 2D masks predicted by zero-shot class-agnostic segmentation models. Contrasted to prior 3D scene segmentation approaches that rely on video object tracking or contrastive learning methods, Gaga utilizes spatial information and effectively associates object masks across diverse camera poses through a novel 3D-aware memory bank. By eliminating the assumption of continuous view changes in training images, Gaga demonstrates robustness to variations in camera poses, particularly beneficial "},"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":"2404.07977","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-11T17:57:19Z","cross_cats_sorted":[],"title_canon_sha256":"87620e4e34f783b2cbae74d033373563ac85f01ce5b2cf75f8bffc315450d0a7","abstract_canon_sha256":"47f04a7cb23e9500f700c19d994146cafa6e93557d626162c614442103daa7f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:50.555816Z","signature_b64":"R0W9kTZXcxp+5cZabbCTpd12M62w9gkhlWrF0O+q9pK/OO91nWc64XWdiikqBr1TGJFJzYITuFpZ5V7M6XFiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c63ac7ac6b8f92bcb47dd8a1c779920de4b2a5869712b280c9cc6b68ff35608","last_reissued_at":"2026-05-29T01:04:50.555266Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:50.555266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaga: Group Any Gaussians via 3D-aware Memory Bank","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhijit Kundu, Ming-Hsuan Yang, Weijie Lyu, Xueting Li, Yi-Hsuan Tsai","submitted_at":"2024-04-11T17:57:19Z","abstract_excerpt":"We introduce Gaga, a framework that reconstructs and segments open-world 3D scenes by leveraging inconsistent 2D masks predicted by zero-shot class-agnostic segmentation models. Contrasted to prior 3D scene segmentation approaches that rely on video object tracking or contrastive learning methods, Gaga utilizes spatial information and effectively associates object masks across diverse camera poses through a novel 3D-aware memory bank. By eliminating the assumption of continuous view changes in training images, Gaga demonstrates robustness to variations in camera poses, particularly beneficial "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07977","kind":"arxiv","version":4},"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/2404.07977/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":"2404.07977","created_at":"2026-05-29T01:04:50.555324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07977v4","created_at":"2026-05-29T01:04:50.555324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07977","created_at":"2026-05-29T01:04:50.555324+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRR2Y6WGXD4S","created_at":"2026-05-29T01:04:50.555324+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRR2Y6WGXD4SXS2H","created_at":"2026-05-29T01:04:50.555324+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRR2Y6WG","created_at":"2026-05-29T01:04:50.555324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":145,"is_internal_anchor":true},{"citing_arxiv_id":"2508.09977","citing_title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2602.21668","citing_title":"Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09662","citing_title":"BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11401","citing_title":"GS4City: Hierarchical Semantic Gaussian Splatting via City-Model Priors","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRR2Y6WGXD4SXS2H3WFBY54ZED","json":"https://pith.science/pith/HRR2Y6WGXD4SXS2H3WFBY54ZED.json","graph_json":"https://pith.science/api/pith-number/HRR2Y6WGXD4SXS2H3WFBY54ZED/graph.json","events_json":"https://pith.science/api/pith-number/HRR2Y6WGXD4SXS2H3WFBY54ZED/events.json","paper":"https://pith.science/paper/HRR2Y6WG"},"agent_actions":{"view_html":"https://pith.science/pith/HRR2Y6WGXD4SXS2H3WFBY54ZED","download_json":"https://pith.science/pith/HRR2Y6WGXD4SXS2H3WFBY54ZED.json","view_paper":"https://pith.science/paper/HRR2Y6WG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07977&json=true","fetch_graph":"https://pith.science/api/pith-number/HRR2Y6WGXD4SXS2H3WFBY54ZED/graph.json","fetch_events":"https://pith.science/api/pith-number/HRR2Y6WGXD4SXS2H3WFBY54ZED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRR2Y6WGXD4SXS2H3WFBY54ZED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRR2Y6WGXD4SXS2H3WFBY54ZED/action/storage_attestation","attest_author":"https://pith.science/pith/HRR2Y6WGXD4SXS2H3WFBY54ZED/action/author_attestation","sign_citation":"https://pith.science/pith/HRR2Y6WGXD4SXS2H3WFBY54ZED/action/citation_signature","submit_replication":"https://pith.science/pith/HRR2Y6WGXD4SXS2H3WFBY54ZED/action/replication_record"}},"created_at":"2026-05-29T01:04:50.555324+00:00","updated_at":"2026-05-29T01:04:50.555324+00:00"}