{"ID":2921889,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-03T23:19:44.77260354Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.01493","arxiv_id":"2606.01493","title":"Splatshot: 3D Face Avatar Generation from a Single Unconstrained Photo","abstract":"Reconstructing a photorealistic 3D face avatar from a single unconstrained photograph is challenging: feed-forward 3D Gaussian Splatting (3DGS) models degrade on out-of-distribution inputs, while pretrained diffusion models produce high-fidelity images but lack multi-view consistency. We observe that these paradigms are fundamentally complementary: explicit 3D representations guarantee geometric consistency, whereas 2D diffusion priors ensure photorealism. Building on this, we propose SplatShot, a training-free framework that couples these representations directly within the denoising process. Given a base 3DGS face model and a single reference image, we jointly denoise all target views using a per-step 3D feedback loop. At each timestep, we predict clean images from the noisy latents, refit the 3DGS to these multi-view predictions, and back-propagate the photometric discrepancy between the 3DGS re-renderings and 2D predictions into the noise estimate. This steers the sampling trajectory toward strictly 3D-coherent, identity-faithful outputs. Experiments on diverse in-the-wild images demonstrate that SplatShot produces 3D avatars with superior identity preservation, photorealism, and multi-view consistency.","short_abstract":"Reconstructing a photorealistic 3D face avatar from a single unconstrained photograph is challenging: feed-forward 3D Gaussian Splatting (3DGS) models degrade on out-of-distribution inputs, while pretrained diffusion models produce high-fidelity images but lack multi-view consistency. We observe that these paradigms ar...","url_abs":"https://arxiv.org/abs/2606.01493","url_pdf":"https://arxiv.org/pdf/2606.01493v1","authors":"[\"Hao Liang\",\"Zhixuan Ge\",\"Soumendu Majee\",\"Joanna Li\",\"Ashok Veeraraghavan\",\"Guha Balakrishnan\"]","published":"2026-05-31T23:19:44Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}