{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BIPH3FBZFIACEPP3GI65QDZDLS","short_pith_number":"pith:BIPH3FBZ","schema_version":"1.0","canonical_sha256":"0a1e7d94392a00223dfb323dd80f235cbf6a07d21b873099e0c966621506eec8","source":{"kind":"arxiv","id":"2104.01148","version":1},"attestation_state":"computed","paper":{"title":"Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Adam R. Kosiorek, Karl Stelzner, Kristian Kersting","submitted_at":"2021-04-02T16:59:29Z","abstract_excerpt":"We present ObSuRF, a method which turns a single image of a scene into a 3D model represented as a set of Neural Radiance Fields (NeRFs), with each NeRF corresponding to a different object. A single forward pass of an encoder network outputs a set of latent vectors describing the objects in the scene. These vectors are used independently to condition a NeRF decoder, defining the geometry and appearance of each object. We make learning more computationally efficient by deriving a novel loss, which allows training NeRFs on RGB-D inputs without explicit ray marching. After confirming that the mod"},"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":"2104.01148","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-02T16:59:29Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c29698076b8f70a27f19815b7e9dc488c7a2e646dfc58e4f798446223e71391b","abstract_canon_sha256":"8d67546bcf2953b7124c18926c4221b99469b344aab4919543b4a45e8e8f03ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:45.079569Z","signature_b64":"wvlN7ca/udMkUeju/9v9KD/N0KHMkCZkPfS10N8KAvOFfvSSb0IiYlDi7mVSNozuk8Ex3ytOMFmNd0GgeFxqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a1e7d94392a00223dfb323dd80f235cbf6a07d21b873099e0c966621506eec8","last_reissued_at":"2026-07-05T02:28:45.079233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:45.079233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Adam R. Kosiorek, Karl Stelzner, Kristian Kersting","submitted_at":"2021-04-02T16:59:29Z","abstract_excerpt":"We present ObSuRF, a method which turns a single image of a scene into a 3D model represented as a set of Neural Radiance Fields (NeRFs), with each NeRF corresponding to a different object. A single forward pass of an encoder network outputs a set of latent vectors describing the objects in the scene. These vectors are used independently to condition a NeRF decoder, defining the geometry and appearance of each object. We make learning more computationally efficient by deriving a novel loss, which allows training NeRFs on RGB-D inputs without explicit ray marching. After confirming that the mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01148","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/2104.01148/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":"2104.01148","created_at":"2026-07-05T02:28:45.079284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01148v1","created_at":"2026-07-05T02:28:45.079284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01148","created_at":"2026-07-05T02:28:45.079284+00:00"},{"alias_kind":"pith_short_12","alias_value":"BIPH3FBZFIAC","created_at":"2026-07-05T02:28:45.079284+00:00"},{"alias_kind":"pith_short_16","alias_value":"BIPH3FBZFIACEPP3","created_at":"2026-07-05T02:28:45.079284+00:00"},{"alias_kind":"pith_short_8","alias_value":"BIPH3FBZ","created_at":"2026-07-05T02:28:45.079284+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19451","citing_title":"3D-DLP: Self-Supervised 3D Object-Centric Scene Representation Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09045","citing_title":"Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BIPH3FBZFIACEPP3GI65QDZDLS","json":"https://pith.science/pith/BIPH3FBZFIACEPP3GI65QDZDLS.json","graph_json":"https://pith.science/api/pith-number/BIPH3FBZFIACEPP3GI65QDZDLS/graph.json","events_json":"https://pith.science/api/pith-number/BIPH3FBZFIACEPP3GI65QDZDLS/events.json","paper":"https://pith.science/paper/BIPH3FBZ"},"agent_actions":{"view_html":"https://pith.science/pith/BIPH3FBZFIACEPP3GI65QDZDLS","download_json":"https://pith.science/pith/BIPH3FBZFIACEPP3GI65QDZDLS.json","view_paper":"https://pith.science/paper/BIPH3FBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01148&json=true","fetch_graph":"https://pith.science/api/pith-number/BIPH3FBZFIACEPP3GI65QDZDLS/graph.json","fetch_events":"https://pith.science/api/pith-number/BIPH3FBZFIACEPP3GI65QDZDLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BIPH3FBZFIACEPP3GI65QDZDLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BIPH3FBZFIACEPP3GI65QDZDLS/action/storage_attestation","attest_author":"https://pith.science/pith/BIPH3FBZFIACEPP3GI65QDZDLS/action/author_attestation","sign_citation":"https://pith.science/pith/BIPH3FBZFIACEPP3GI65QDZDLS/action/citation_signature","submit_replication":"https://pith.science/pith/BIPH3FBZFIACEPP3GI65QDZDLS/action/replication_record"}},"created_at":"2026-07-05T02:28:45.079284+00:00","updated_at":"2026-07-05T02:28:45.079284+00:00"}