{"ID":2855407,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.14081","arxiv_id":"2510.14081","title":"Capture, Canonicalize, Splat: Zero-Shot 3D Gaussian Avatars from Unstructured Phone Images","abstract":"We present a novel, zero-shot pipeline for creating hyperrealistic, identity-preserving 3D avatars from a few unstructured phone images. Existing methods face several challenges: single-view approaches suffer from geometric inconsistencies and hallucinations, degrading identity preservation, while models trained on synthetic data fail to capture high-frequency details like skin wrinkles and fine hair, limiting realism. Our method introduces two key contributions: (1) a generative canonicalization module that processes multiple unstructured views into a standardized, consistent representation, and (2) a transformer-based model trained on a new, large-scale dataset of high-fidelity Gaussian splatting avatars derived from dome captures of real people. This \"Capture, Canonicalize, Splat\" pipeline produces static quarter-body avatars with compelling realism and robust identity preservation from unstructured photos.","short_abstract":"We present a novel, zero-shot pipeline for creating hyperrealistic, identity-preserving 3D avatars from a few unstructured phone images. Existing methods face several challenges: single-view approaches suffer from geometric inconsistencies and hallucinations, degrading identity preservation, while models trained on syn...","url_abs":"https://arxiv.org/abs/2510.14081","url_pdf":"https://arxiv.org/pdf/2510.14081v3","authors":"[\"Emanuel Garbin\",\"Guy Adam\",\"Oded Krams\",\"Zohar Barzelay\",\"Eran Guendelman\",\"Michael Schwarz\",\"Matteo Presutto\",\"Moran Vatelmacher\",\"Yigal Shenkman\",\"Eli Peker\",\"Itai Druker\",\"Uri Patish\",\"Yoav Blum\",\"Max Bluvstein\",\"Junxuan Li\",\"Rawal Khirodkar\",\"Shunsuke Saito\"]","published":"2025-10-15T20:36:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.GR\"]","methods":"[\"Transformer\"]","has_code":false}