YoNoSplat

YoNoSplat: You Only Need One Model for
Feedforward 3D Gaussian Splatting

Botao Ye1,2     Boqi Chen1,2     Haofei Xu1     Daniel Barath1     Marc Pollefeys1,3

ICLR 2026

1ETH Zurich     2ETH AI Center     3Microsoft    

YoNoSplat reconstructs 3D Gaussian splats directly from unposed and uncalibrated images, while flexibly leveraging ground-truth camera poses or intrinsics when available.

Work in progress The project page is still under construction (stay tuned!).

Pose-free, feed-forward novel view synthesis on unseen scenes with varying numbers of input views.

BibTeX

@inproceedings{yonosplat,
      title={YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting},
      author={Ye, Botao and Chen, Boqi and Xu, Haofei and Barath, Daniel and Pollefeys, Marc},
      booktitle={International Conference on Learning Representations (ICLR)},
      year={2026}
    }

awesome webpage template