English

GIGA: Generalizable Sparse Image-driven Gaussian Humans

Image and Video Processing 2025-08-26 v2

Abstract

Driving a high-quality and photorealistic full-body virtual human from a few RGB cameras is a challenging problem that has become increasingly relevant with emerging virtual reality technologies. A promising solution to democratize such technology would be a generalizable method that takes sparse multi-view images of any person and then generates photoreal free-view renderings of them. However, the state-of-the-art approaches are not scalable to very large datasets and, thus, lack diversity and photorealism. To address this problem, we propose GIGA, a novel, generalizable full-body model for rendering photoreal humans in free viewpoint, driven by a single-view or sparse multi-view video. Notably, GIGA can scale training to a few thousand subjects while maintaining high photorealism and synthesizing dynamic appearance. At the core, we introduce a MultiHeadUNet architecture, which takes an approximate RGB texture accumulated from a single or multiple sparse views and predicts 3D Gaussian primitives represented as 2D texels on top of a human body mesh. At test time, our method performs novel view synthesis of a virtual 3D Gaussian-based human from 1 to 4 input views and a tracked body template for unseen identities. Our method excels over prior works by a significant margin in terms of identity generalization capability and photorealism.

Keywords

Cite

@article{arxiv.2504.07144,
  title  = {GIGA: Generalizable Sparse Image-driven Gaussian Humans},
  author = {Anton Zubekhin and Heming Zhu and Paulo Gotardo and Thabo Beeler and Marc Habermann and Christian Theobalt},
  journal= {arXiv preprint arXiv:2504.07144},
  year   = {2025}
}

Comments

15 pages, 10 figures, project page: https://vcai.mpi-inf.mpg.de/projects/GIGA

R2 v1 2026-06-28T22:52:44.099Z