{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YXI2Q5MGRGBZBO54RG42X45FUI","short_pith_number":"pith:YXI2Q5MG","schema_version":"1.0","canonical_sha256":"c5d1a87586898390bbbc89b9abf3a5a20681967ba080fd53aa1f36e750ea2fb6","source":{"kind":"arxiv","id":"2508.19247","version":1},"attestation_state":"computed","paper":{"title":"VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunchao Guo, Gengxiong Zhuang, Haoran Feng, Lin Li, Lu Sheng, Rui Chen, Zehuan Huang","submitted_at":"2025-08-26T17:59:47Z","abstract_excerpt":"3D local editing of specified regions is crucial for game industry and robot interaction. Recent methods typically edit rendered multi-view images and then reconstruct 3D models, but they face challenges in precisely preserving unedited regions and overall coherence. Inspired by structured 3D generative models, we propose VoxHammer, a novel training-free approach that performs precise and coherent editing in 3D latent space. Given a 3D model, VoxHammer first predicts its inversion trajectory and obtains its inverted latents and key-value tokens at each timestep. Subsequently, in the denoising "},"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":"2508.19247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-26T17:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"245ac50d83dd96cb676b258dcf789bbc466a8eb2e09f15191d65ec61c0424e43","abstract_canon_sha256":"b776f13228954bddc161405328874de0e3cd3150fb8c35ae21b9ebe52da23a18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:40.426818Z","signature_b64":"+rPymFqYh01fMLQSpqn4STePsLSTbWhOvq7K+Kqs9y8k8QarDgbajzbJdFa7rSCKj6M8XSF5t+0Xmo7EOpKICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5d1a87586898390bbbc89b9abf3a5a20681967ba080fd53aa1f36e750ea2fb6","last_reissued_at":"2026-07-05T11:59:40.426350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:40.426350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunchao Guo, Gengxiong Zhuang, Haoran Feng, Lin Li, Lu Sheng, Rui Chen, Zehuan Huang","submitted_at":"2025-08-26T17:59:47Z","abstract_excerpt":"3D local editing of specified regions is crucial for game industry and robot interaction. Recent methods typically edit rendered multi-view images and then reconstruct 3D models, but they face challenges in precisely preserving unedited regions and overall coherence. Inspired by structured 3D generative models, we propose VoxHammer, a novel training-free approach that performs precise and coherent editing in 3D latent space. Given a 3D model, VoxHammer first predicts its inversion trajectory and obtains its inverted latents and key-value tokens at each timestep. Subsequently, in the denoising "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19247","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/2508.19247/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":"2508.19247","created_at":"2026-07-05T11:59:40.426407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19247v1","created_at":"2026-07-05T11:59:40.426407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19247","created_at":"2026-07-05T11:59:40.426407+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXI2Q5MGRGBZ","created_at":"2026-07-05T11:59:40.426407+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXI2Q5MGRGBZBO54","created_at":"2026-07-05T11:59:40.426407+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXI2Q5MG","created_at":"2026-07-05T11:59:40.426407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07187","citing_title":"EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07115","citing_title":"3DMorph: Single-Image-Guided Local 3D Shape Editing and Morphing","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05142","citing_title":"GeM-NR: Geometry-Aware Multi-View Editing for Nonrigid Scene Changes","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23178","citing_title":"Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28134","citing_title":"MeshReGen: A Unified 3D Geometry Regeneration Framework","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16745","citing_title":"EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16767","citing_title":"Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2601.11194","citing_title":"ATATA: One Algorithm to Align Them All","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04349","citing_title":"VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2603.16869","citing_title":"SegviGen: Repurposing 3D Generative Model for Part Segmentation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28134","citing_title":"MeshReGen: A Unified 3D Geometry Regeneration Framework","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27504","citing_title":"REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07385","citing_title":"Velocity-Space 3D Asset Editing","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13688","citing_title":"Beyond Voxel 3D Editing: Learning from 3D Masks and Self-Constructed Data","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14914","citing_title":"Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YXI2Q5MGRGBZBO54RG42X45FUI","json":"https://pith.science/pith/YXI2Q5MGRGBZBO54RG42X45FUI.json","graph_json":"https://pith.science/api/pith-number/YXI2Q5MGRGBZBO54RG42X45FUI/graph.json","events_json":"https://pith.science/api/pith-number/YXI2Q5MGRGBZBO54RG42X45FUI/events.json","paper":"https://pith.science/paper/YXI2Q5MG"},"agent_actions":{"view_html":"https://pith.science/pith/YXI2Q5MGRGBZBO54RG42X45FUI","download_json":"https://pith.science/pith/YXI2Q5MGRGBZBO54RG42X45FUI.json","view_paper":"https://pith.science/paper/YXI2Q5MG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19247&json=true","fetch_graph":"https://pith.science/api/pith-number/YXI2Q5MGRGBZBO54RG42X45FUI/graph.json","fetch_events":"https://pith.science/api/pith-number/YXI2Q5MGRGBZBO54RG42X45FUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXI2Q5MGRGBZBO54RG42X45FUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXI2Q5MGRGBZBO54RG42X45FUI/action/storage_attestation","attest_author":"https://pith.science/pith/YXI2Q5MGRGBZBO54RG42X45FUI/action/author_attestation","sign_citation":"https://pith.science/pith/YXI2Q5MGRGBZBO54RG42X45FUI/action/citation_signature","submit_replication":"https://pith.science/pith/YXI2Q5MGRGBZBO54RG42X45FUI/action/replication_record"}},"created_at":"2026-07-05T11:59:40.426407+00:00","updated_at":"2026-07-05T11:59:40.426407+00:00"}