{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BGVVDENO64ZR5QZ4DCYKMLPPMX","short_pith_number":"pith:BGVVDENO","schema_version":"1.0","canonical_sha256":"09ab5191aef7331ec33c18b0a62def65e16c6931782a6fb9f39495ce4771720c","source":{"kind":"arxiv","id":"2503.22236","version":2},"attestation_state":"computed","paper":{"title":"Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Chongjie Ye, Hao Zhao, Jiahao Chang, Jiaqing Zhou, Xiaoguang Han, Xiaoyang Guo, Yushuang Wu, Ziteng Lu","submitted_at":"2025-03-28T08:39:20Z","abstract_excerpt":"With the growing demand for high-fidelity 3D models from 2D images, existing methods still face significant challenges in accurately reproducing fine-grained geometric details due to limitations in domain gaps and inherent ambiguities in RGB images. To address these issues, we propose Hi3DGen, a novel framework for generating high-fidelity 3D geometry from images via normal bridging. Hi3DGen consists of three key components: (1) an image-to-normal estimator that decouples the low-high frequency image pattern with noise injection and dual-stream training to achieve generalizable, stable, and sh"},"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":"2503.22236","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2025-03-28T08:39:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d98b7ff57f20f2bf56b03b62717e87f90b0bfed14a7bc270ce1d3d82223fe65b","abstract_canon_sha256":"3908ac7ba61b40ce3bc6573e4d01a291b13510ae48ec4f8b84e75fc0ecae603c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:55.069004Z","signature_b64":"97EBpuP4PuCqXk+af8Osx+0S2sD1vsrtUVu6LYZVh3aLqfkhTRXEVuF2g0Adn8qasHNXu6PrAtq95haTIBOCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09ab5191aef7331ec33c18b0a62def65e16c6931782a6fb9f39495ce4771720c","last_reissued_at":"2026-07-05T10:41:55.068520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:55.068520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.GR","authors_text":"Chongjie Ye, Hao Zhao, Jiahao Chang, Jiaqing Zhou, Xiaoguang Han, Xiaoyang Guo, Yushuang Wu, Ziteng Lu","submitted_at":"2025-03-28T08:39:20Z","abstract_excerpt":"With the growing demand for high-fidelity 3D models from 2D images, existing methods still face significant challenges in accurately reproducing fine-grained geometric details due to limitations in domain gaps and inherent ambiguities in RGB images. To address these issues, we propose Hi3DGen, a novel framework for generating high-fidelity 3D geometry from images via normal bridging. Hi3DGen consists of three key components: (1) an image-to-normal estimator that decouples the low-high frequency image pattern with noise injection and dual-stream training to achieve generalizable, stable, and sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22236","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/2503.22236/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":"2503.22236","created_at":"2026-07-05T10:41:55.068578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22236v2","created_at":"2026-07-05T10:41:55.068578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22236","created_at":"2026-07-05T10:41:55.068578+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGVVDENO64ZR","created_at":"2026-07-05T10:41:55.068578+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGVVDENO64ZR5QZ4","created_at":"2026-07-05T10:41:55.068578+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGVVDENO","created_at":"2026-07-05T10:41:55.068578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06565","citing_title":"ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation","ref_index":97,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24301","citing_title":"MM-TRELLIS: Point-Cloud Guided Multi-Modal 3D Vehicle Generation in Autonomous Driving","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27305","citing_title":"Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31109","citing_title":"InfiniVerse: Occupancy Guided Unbounded Scene Generation for Autonomous Driving","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28060","citing_title":"ReScene: Structured Indoor Scene Reconstruction from Multi-View Captures","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23381","citing_title":"VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14692","citing_title":"Native and Compact Structured Latents for 3D Generation","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21121","citing_title":"ROAR-3D: Routing Arbitrary Views for High-Fidelity 3D Generation","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15843","citing_title":"WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16767","citing_title":"Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01479","citing_title":"UniRecGen: Unifying Multi-View 3D Reconstruction and Generation","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03359","citing_title":"Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26917","citing_title":"AnimateAnyMesh++: A Flexible 4D Foundation Model for High-Fidelity Text-Driven Mesh Animation","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10204","citing_title":"3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10922","citing_title":"Pixal3D: Pixel-Aligned 3D Generation from Images","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03623","citing_title":"A Few-Step Generative Model on Cumulative Flow Maps","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12929","citing_title":"Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10789","citing_title":"ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGVVDENO64ZR5QZ4DCYKMLPPMX","json":"https://pith.science/pith/BGVVDENO64ZR5QZ4DCYKMLPPMX.json","graph_json":"https://pith.science/api/pith-number/BGVVDENO64ZR5QZ4DCYKMLPPMX/graph.json","events_json":"https://pith.science/api/pith-number/BGVVDENO64ZR5QZ4DCYKMLPPMX/events.json","paper":"https://pith.science/paper/BGVVDENO"},"agent_actions":{"view_html":"https://pith.science/pith/BGVVDENO64ZR5QZ4DCYKMLPPMX","download_json":"https://pith.science/pith/BGVVDENO64ZR5QZ4DCYKMLPPMX.json","view_paper":"https://pith.science/paper/BGVVDENO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22236&json=true","fetch_graph":"https://pith.science/api/pith-number/BGVVDENO64ZR5QZ4DCYKMLPPMX/graph.json","fetch_events":"https://pith.science/api/pith-number/BGVVDENO64ZR5QZ4DCYKMLPPMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGVVDENO64ZR5QZ4DCYKMLPPMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGVVDENO64ZR5QZ4DCYKMLPPMX/action/storage_attestation","attest_author":"https://pith.science/pith/BGVVDENO64ZR5QZ4DCYKMLPPMX/action/author_attestation","sign_citation":"https://pith.science/pith/BGVVDENO64ZR5QZ4DCYKMLPPMX/action/citation_signature","submit_replication":"https://pith.science/pith/BGVVDENO64ZR5QZ4DCYKMLPPMX/action/replication_record"}},"created_at":"2026-07-05T10:41:55.068578+00:00","updated_at":"2026-07-05T10:41:55.068578+00:00"}