{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OK5YOJQZGAZI2MA5D2JGQ7WBUK","short_pith_number":"pith:OK5YOJQZ","schema_version":"1.0","canonical_sha256":"72bb87261930328d301d1e92687ec1a28ce94462ee8886c379d9eadbe92505aa","source":{"kind":"arxiv","id":"2411.18473","version":2},"attestation_state":"computed","paper":{"title":"HEMGS: A Hybrid Entropy Model for 3D Gaussian Splatting Data Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Xu, Lei Liu, Wei Jiang, Wei Wang, Zhenghao Chen","submitted_at":"2024-11-27T16:08:59Z","abstract_excerpt":"In this work, we propose a novel compression framework for 3D Gaussian Splatting (3DGS) data. Building on anchor-based 3DGS methodologies, our approach compresses all attributes within each anchor by introducing a novel Hybrid Entropy Model for 3D Gaussian Splatting (HEMGS) to achieve hybrid lossy-lossless compression. It consists of three main components: a variable-rate predictor, a hyperprior network, and an autoregressive network. First, unlike previous methods that adopt multiple models to achieve multi-rate lossy compression, thereby increasing training overhead, our variable-rate predic"},"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":"2411.18473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T16:08:59Z","cross_cats_sorted":[],"title_canon_sha256":"b40d2a0cc68255d3bd81ca03e87fb7dc406d71306256b69d0088d459a2881cfb","abstract_canon_sha256":"7cfc96b47dee28eae186559d79d1f1f0b8d2cc8e03bf79195dec328884a1fd63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:16.579206Z","signature_b64":"l0FUinPPPa5uEv5y4mJUaiH17a2jyYByv1JoziL2rlLG5jxMW89a22NFjDg5eCndYl8EpijtT0OeWfJbirTlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72bb87261930328d301d1e92687ec1a28ce94462ee8886c379d9eadbe92505aa","last_reissued_at":"2026-07-05T10:52:16.578696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:16.578696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HEMGS: A Hybrid Entropy Model for 3D Gaussian Splatting Data Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Xu, Lei Liu, Wei Jiang, Wei Wang, Zhenghao Chen","submitted_at":"2024-11-27T16:08:59Z","abstract_excerpt":"In this work, we propose a novel compression framework for 3D Gaussian Splatting (3DGS) data. Building on anchor-based 3DGS methodologies, our approach compresses all attributes within each anchor by introducing a novel Hybrid Entropy Model for 3D Gaussian Splatting (HEMGS) to achieve hybrid lossy-lossless compression. It consists of three main components: a variable-rate predictor, a hyperprior network, and an autoregressive network. First, unlike previous methods that adopt multiple models to achieve multi-rate lossy compression, thereby increasing training overhead, our variable-rate predic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18473","kind":"arxiv","version":2},"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/2411.18473/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":"2411.18473","created_at":"2026-07-05T10:52:16.578757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18473v2","created_at":"2026-07-05T10:52:16.578757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18473","created_at":"2026-07-05T10:52:16.578757+00:00"},{"alias_kind":"pith_short_12","alias_value":"OK5YOJQZGAZI","created_at":"2026-07-05T10:52:16.578757+00:00"},{"alias_kind":"pith_short_16","alias_value":"OK5YOJQZGAZI2MA5","created_at":"2026-07-05T10:52:16.578757+00:00"},{"alias_kind":"pith_short_8","alias_value":"OK5YOJQZ","created_at":"2026-07-05T10:52:16.578757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11782","citing_title":"Seeing What Matters: Perceptual Wrapper with Common Randomness for 3D Gaussian Splatting","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13482","citing_title":"Improving 3D Gaussian Splatting Compression by Scene-Adaptive Lattice Vector Quantization","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04549","citing_title":"Nix and Fix: Targeting 1000x Compression of 3D Gaussian Splatting with Diffusion Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26799","citing_title":"MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26799","citing_title":"MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11685","citing_title":"Unfolding 3D Gaussian Splatting via Iterative Gaussian Synopsis","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26799","citing_title":"MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26799","citing_title":"MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OK5YOJQZGAZI2MA5D2JGQ7WBUK","json":"https://pith.science/pith/OK5YOJQZGAZI2MA5D2JGQ7WBUK.json","graph_json":"https://pith.science/api/pith-number/OK5YOJQZGAZI2MA5D2JGQ7WBUK/graph.json","events_json":"https://pith.science/api/pith-number/OK5YOJQZGAZI2MA5D2JGQ7WBUK/events.json","paper":"https://pith.science/paper/OK5YOJQZ"},"agent_actions":{"view_html":"https://pith.science/pith/OK5YOJQZGAZI2MA5D2JGQ7WBUK","download_json":"https://pith.science/pith/OK5YOJQZGAZI2MA5D2JGQ7WBUK.json","view_paper":"https://pith.science/paper/OK5YOJQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18473&json=true","fetch_graph":"https://pith.science/api/pith-number/OK5YOJQZGAZI2MA5D2JGQ7WBUK/graph.json","fetch_events":"https://pith.science/api/pith-number/OK5YOJQZGAZI2MA5D2JGQ7WBUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OK5YOJQZGAZI2MA5D2JGQ7WBUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OK5YOJQZGAZI2MA5D2JGQ7WBUK/action/storage_attestation","attest_author":"https://pith.science/pith/OK5YOJQZGAZI2MA5D2JGQ7WBUK/action/author_attestation","sign_citation":"https://pith.science/pith/OK5YOJQZGAZI2MA5D2JGQ7WBUK/action/citation_signature","submit_replication":"https://pith.science/pith/OK5YOJQZGAZI2MA5D2JGQ7WBUK/action/replication_record"}},"created_at":"2026-07-05T10:52:16.578757+00:00","updated_at":"2026-07-05T10:52:16.578757+00:00"}