{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KWPSV3JFKBAQYHJY7XIUWCM22P","short_pith_number":"pith:KWPSV3JF","schema_version":"1.0","canonical_sha256":"559f2aed2550410c1d38fdd14b099ad3eaa0fb83fca67b1c1beb3ec4228833b0","source":{"kind":"arxiv","id":"2406.09292","version":2},"attestation_state":"computed","paper":{"title":"Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Drew A. Hudson, Igor Gilitschenski, Kelsey R. Allen, Rishabh Kabra, Sjoerd van Steenkiste, Thomas Kipf, Yulia Rubanova, Yusuf Aytar, Ziyi Wu","submitted_at":"2024-06-13T16:29:18Z","abstract_excerpt":"We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, Neural Assets, to control the 3D pose of individual objects in a scene. Neural Assets are obtained by pooling visual representations of objects from a reference image, such as a frame in a video, and are trained to reconstruct the respective objects in a different image, e.g., a later frame in the video. Importantly, we encode object visuals from the reference image while conditioning on object poses from "},"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":"2406.09292","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T16:29:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5642ccd1bd9a9a068e498880e5ef9e05d08b50d4cb03457b128efc61badd09de","abstract_canon_sha256":"3078b49cb03f30b16ed04c5f5538e312978d8a3096ec77da8f03367714502e6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:23.101078Z","signature_b64":"dVW9HwqYG7iFeGwWo8EwBWjTfdTpvkgcVhSuhbEKihebA2xN9WsAQa5bCOq8xMGq6gfokdW21qwcGWfsqgodCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"559f2aed2550410c1d38fdd14b099ad3eaa0fb83fca67b1c1beb3ec4228833b0","last_reissued_at":"2026-07-05T09:27:23.100566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:23.100566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Drew A. Hudson, Igor Gilitschenski, Kelsey R. Allen, Rishabh Kabra, Sjoerd van Steenkiste, Thomas Kipf, Yulia Rubanova, Yusuf Aytar, Ziyi Wu","submitted_at":"2024-06-13T16:29:18Z","abstract_excerpt":"We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, Neural Assets, to control the 3D pose of individual objects in a scene. Neural Assets are obtained by pooling visual representations of objects from a reference image, such as a frame in a video, and are trained to reconstruct the respective objects in a different image, e.g., a later frame in the video. Importantly, we encode object visuals from the reference image while conditioning on object poses from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09292","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/2406.09292/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":"2406.09292","created_at":"2026-07-05T09:27:23.100628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09292v2","created_at":"2026-07-05T09:27:23.100628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09292","created_at":"2026-07-05T09:27:23.100628+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWPSV3JFKBAQ","created_at":"2026-07-05T09:27:23.100628+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWPSV3JFKBAQYHJY","created_at":"2026-07-05T09:27:23.100628+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWPSV3JF","created_at":"2026-07-05T09:27:23.100628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.10273","citing_title":"How to Spin an Object: First, Get the Shape Right","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWPSV3JFKBAQYHJY7XIUWCM22P","json":"https://pith.science/pith/KWPSV3JFKBAQYHJY7XIUWCM22P.json","graph_json":"https://pith.science/api/pith-number/KWPSV3JFKBAQYHJY7XIUWCM22P/graph.json","events_json":"https://pith.science/api/pith-number/KWPSV3JFKBAQYHJY7XIUWCM22P/events.json","paper":"https://pith.science/paper/KWPSV3JF"},"agent_actions":{"view_html":"https://pith.science/pith/KWPSV3JFKBAQYHJY7XIUWCM22P","download_json":"https://pith.science/pith/KWPSV3JFKBAQYHJY7XIUWCM22P.json","view_paper":"https://pith.science/paper/KWPSV3JF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09292&json=true","fetch_graph":"https://pith.science/api/pith-number/KWPSV3JFKBAQYHJY7XIUWCM22P/graph.json","fetch_events":"https://pith.science/api/pith-number/KWPSV3JFKBAQYHJY7XIUWCM22P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWPSV3JFKBAQYHJY7XIUWCM22P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWPSV3JFKBAQYHJY7XIUWCM22P/action/storage_attestation","attest_author":"https://pith.science/pith/KWPSV3JFKBAQYHJY7XIUWCM22P/action/author_attestation","sign_citation":"https://pith.science/pith/KWPSV3JFKBAQYHJY7XIUWCM22P/action/citation_signature","submit_replication":"https://pith.science/pith/KWPSV3JFKBAQYHJY7XIUWCM22P/action/replication_record"}},"created_at":"2026-07-05T09:27:23.100628+00:00","updated_at":"2026-07-05T09:27:23.100628+00:00"}