{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IYOYWPMF7QHOZMHFGOBWSHR62Z","short_pith_number":"pith:IYOYWPMF","schema_version":"1.0","canonical_sha256":"461d8b3d85fc0eecb0e53383691e3ed668800d8872465a814e2e66fa75225ceb","source":{"kind":"arxiv","id":"2508.13154","version":1},"attestation_state":"computed","paper":{"title":"4DNeX: Feed-Forward 4D Generative Modeling Made Easy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, He Zhu, Jiawei Ren, Liang Pan, Long Zhuo, Tianqi Liu, Zeng Tao, Zhaoxi Chen, Ziwei Liu","submitted_at":"2025-08-18T17:59:55Z","abstract_excerpt":"We present 4DNeX, the first feed-forward framework for generating 4D (i.e., dynamic 3D) scene representations from a single image. In contrast to existing methods that rely on computationally intensive optimization or require multi-frame video inputs, 4DNeX enables efficient, end-to-end image-to-4D generation by fine-tuning a pretrained video diffusion model. Specifically, 1) to alleviate the scarcity of 4D data, we construct 4DNeX-10M, a large-scale dataset with high-quality 4D annotations generated using advanced reconstruction approaches. 2) we introduce a unified 6D video representation th"},"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":"2508.13154","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T17:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"957c564ac8fd845839300c37d37c818402c89dc8eb152cca9fd01d8c85ee597e","abstract_canon_sha256":"4bb1cc0a552028a48dc77c4a81c3f1084937011c89708ebd8534520fe7eb92d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:33.388878Z","signature_b64":"r69Km3F7H1QBKIZ2yPceLrb5klJmtwYog2C+2KRsbBpSZ4Rb6R9+5YQVysZFywEwkmcOoWKGNpSyrUqoCCgiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"461d8b3d85fc0eecb0e53383691e3ed668800d8872465a814e2e66fa75225ceb","last_reissued_at":"2026-07-05T11:55:33.388387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:33.388387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"4DNeX: Feed-Forward 4D Generative Modeling Made Easy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangzhou Hong, He Zhu, Jiawei Ren, Liang Pan, Long Zhuo, Tianqi Liu, Zeng Tao, Zhaoxi Chen, Ziwei Liu","submitted_at":"2025-08-18T17:59:55Z","abstract_excerpt":"We present 4DNeX, the first feed-forward framework for generating 4D (i.e., dynamic 3D) scene representations from a single image. In contrast to existing methods that rely on computationally intensive optimization or require multi-frame video inputs, 4DNeX enables efficient, end-to-end image-to-4D generation by fine-tuning a pretrained video diffusion model. Specifically, 1) to alleviate the scarcity of 4D data, we construct 4DNeX-10M, a large-scale dataset with high-quality 4D annotations generated using advanced reconstruction approaches. 2) we introduce a unified 6D video representation th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13154","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/2508.13154/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":"2508.13154","created_at":"2026-07-05T11:55:33.388446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13154v1","created_at":"2026-07-05T11:55:33.388446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13154","created_at":"2026-07-05T11:55:33.388446+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYOYWPMF7QHO","created_at":"2026-07-05T11:55:33.388446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYOYWPMF7QHOZMHF","created_at":"2026-07-05T11:55:33.388446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYOYWPMF","created_at":"2026-07-05T11:55:33.388446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06559","citing_title":"RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01896","citing_title":"Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03943","citing_title":"PointAction: 3D Points as Universal Action Representations for Robot Control","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29333","citing_title":"HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24764","citing_title":"World-R1: Reinforcing 3D Constraints for Text-to-Video Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24764","citing_title":"World-R1: Reinforcing 3D Constraints for Text-to-Video Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00503","citing_title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24764","citing_title":"World-R1: Reinforcing 3D Constraints for Text-to-Video Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05207","citing_title":"Syn4D: A Multiview Synthetic 4D Dataset","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01896","citing_title":"Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07390","citing_title":"ST-Gen4D: Embedding 4D Spatiotemporal Cognition into World Model for 4D Generation","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IYOYWPMF7QHOZMHFGOBWSHR62Z","json":"https://pith.science/pith/IYOYWPMF7QHOZMHFGOBWSHR62Z.json","graph_json":"https://pith.science/api/pith-number/IYOYWPMF7QHOZMHFGOBWSHR62Z/graph.json","events_json":"https://pith.science/api/pith-number/IYOYWPMF7QHOZMHFGOBWSHR62Z/events.json","paper":"https://pith.science/paper/IYOYWPMF"},"agent_actions":{"view_html":"https://pith.science/pith/IYOYWPMF7QHOZMHFGOBWSHR62Z","download_json":"https://pith.science/pith/IYOYWPMF7QHOZMHFGOBWSHR62Z.json","view_paper":"https://pith.science/paper/IYOYWPMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13154&json=true","fetch_graph":"https://pith.science/api/pith-number/IYOYWPMF7QHOZMHFGOBWSHR62Z/graph.json","fetch_events":"https://pith.science/api/pith-number/IYOYWPMF7QHOZMHFGOBWSHR62Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYOYWPMF7QHOZMHFGOBWSHR62Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYOYWPMF7QHOZMHFGOBWSHR62Z/action/storage_attestation","attest_author":"https://pith.science/pith/IYOYWPMF7QHOZMHFGOBWSHR62Z/action/author_attestation","sign_citation":"https://pith.science/pith/IYOYWPMF7QHOZMHFGOBWSHR62Z/action/citation_signature","submit_replication":"https://pith.science/pith/IYOYWPMF7QHOZMHFGOBWSHR62Z/action/replication_record"}},"created_at":"2026-07-05T11:55:33.388446+00:00","updated_at":"2026-07-05T11:55:33.388446+00:00"}