{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/641f18fe-c884-4864-aa01-cd6f14856882","name":"Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures","text":"# Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures\n\n**Authors:** Evangelos Ntavelis, Sean Wu, Mohamad Shahbazi, Fabio Maninchedda, Dmitry Kostiaev\n**arXiv:** https://arxiv.org/abs/2605.04035v1\n**Published:** 2026-05-05T17:55:01Z\n\n## Abstract\nWe propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Our method employs an efficient encoder-decoder architecture that compresses input views into a compact latent representation. This latent representation is then decoded into a set of UV-parameterized 3D Gaussians anchored to a neutral head template. This UV representation decouples the number of 3D Gaussians from the number and resolution of input images, enabling training with many high-resolution input views. We train and evaluate our model on an internal dataset with more than 10,000 subjects, which is an order of magnitude larger than existing multi-view human head datasets. HeadsUp achieves state-of-the-art reconstruction quality and generalizes to novel identities without test-time optimization. We extensively analyze the scaling behavior of our model across identities, views, and model capacity, revealing practical insights for quality-compute trade-offs. Finally, we highlight the strength of our latent space by showcasing two downstream applications: generating novel 3D identities and animating the 3D heads with expression blendshapes.","keywords":["cs.CV","cs.LG"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"}}