{"paper":{"title":"Texture Regenerating and Grafting Using Genome-Driven Neural Cellular Automata","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Neural cellular automata can self-regenerate damaged textures and graft distinct ones together by initializing genome channels at inference time.","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Alexandra B\\u{a}icoianu, Ioana Cristina Plajer, Mirela-Magdalena Catrina","submitted_at":"2026-05-13T14:57:32Z","abstract_excerpt":"This study significantly advances multi-texture synthesis using Neural Cellular Automata (NCAs) by introducing a novel training methodology that enables robust self-regeneration of textures in damaged regions. This inherent healing mechanism, essential for dynamic and adaptive systems, extends beyond traditional computer graphics applications, highlighting the fundamental self-organizing properties of NCAs. Furthermore, we present a versatile grafting technique, enabling the seamless combination of distinct textures. This is achieved efficiently during the inference phase, without requiring sp"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"A novel training methodology enables robust self-regeneration of textures in damaged regions, and a grafting technique achieves seamless combination of distinct textures efficiently during the inference phase without requiring specialized retraining, through precise initialization of the NCA's genome channels.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That precise initialization of genome channels in the NCA allows seamless, high-quality grafting of arbitrary distinct textures at inference time without retraining or visible artifacts, and that the self-regeneration mechanism remains robust across varied damage patterns and texture complexities.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Neural cellular automata can be trained for robust self-regeneration of damaged textures and for efficient grafting of multiple textures at inference time via genome channel initialization.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Neural cellular automata can self-regenerate damaged textures and graft distinct ones together by initializing genome channels at inference time.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c67db719bfbf42622b6e4d0f1b7a420fb9e74b20b2e98f4794ed90034043538c"},"source":{"id":"2605.13630","kind":"arxiv","version":1},"verdict":{"id":"23a67bcd-b106-4be1-99fb-a44e450fb212","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:17:28.556140Z","strongest_claim":"A novel training methodology enables robust self-regeneration of textures in damaged regions, and a grafting technique achieves seamless combination of distinct textures efficiently during the inference phase without requiring specialized retraining, through precise initialization of the NCA's genome channels.","one_line_summary":"Neural cellular automata can be trained for robust self-regeneration of damaged textures and for efficient grafting of multiple textures at inference time via genome channel initialization.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That precise initialization of genome channels in the NCA allows seamless, high-quality grafting of arbitrary distinct textures at inference time without retraining or visible artifacts, and that the self-regeneration mechanism remains robust across varied damage patterns and texture complexities.","pith_extraction_headline":"Neural cellular automata can self-regenerate damaged textures and graft distinct ones together by initializing genome channels at inference time."},"references":{"count":29,"sample":[{"doi":"","year":2026,"title":"Texture Regenerating and Grafting Using Genome-Driven Neural Cellular Automata","work_id":"ac6f26ac-87dc-4e51-8181-2ab3416b8211","ref_index":1,"cited_arxiv_id":"2605.13630","is_internal_anchor":true},{"doi":"","year":null,"title":"MA TERIALS AND METHODS 2.1. Previous work The fundamental architecture of the NCA employed for tex- ture synthesis is extensively detailed in [13] and will thus be concisely reviewed herein for contex","work_id":"23aadd15-a941-4cad-890c-b1fac323c2eb","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Here, damaging refers to randomizing the state vectors of cells con- tained within a circular region of radius 15 to 25 pixels","work_id":"8cfb80af-8b38-435c-a214-f01ddb024349","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The examples utilize an NCA trained on sets of 4 or 8 textures, as those illustrated in Fig","work_id":"b883aac0-3310-4746-84a9-d8c9b5e75149","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"This approach involves initializing a single NCA at timestampt= 0","work_id":"d8bdd342-8eeb-4392-939e-36b9331982b2","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":29,"snapshot_sha256":"25ca9601a994d9fea57165bcb010380d782716a65d00d423fdf7088c64f84664","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5a12c309b1c0cb72835f5466b5023825646ce4377e2e44f2894b29c3f4c41391"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}