---
license: mit
---

<p align="center">
  <h2 align="center">YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting</h2>
 <p align="center">
    <a href="https://botaoye.github.io/">Botao Ye</a>
    ·
    <a href="https://scholar.google.com/citations?user=eAR23MAAAAAJ&hl=en">Boqi Chen</a>
    ·
    <a href="https://haofeixu.github.io/">Haofei Xu</a>
    ·
    <a href="https://cvg.ethz.ch/team/Dr-Daniel-Bela-Barath/">Daniel Barath</a>
    ·
    <a href="https://people.inf.ethz.ch/marc.pollefeys/">Marc Pollefeys</a>
  </p>
  <p align="center">
    <a href="https://arxiv.org/abs/2511.07321"><img src="https://img.shields.io/badge/arXiv-2511.07321-b31b1b.svg" alt="arXiv"></a>
    &nbsp;
    <a href="https://botaoye.github.io/yonosplat/"><img src="https://img.shields.io/badge/Project-Page-green.svg" alt="Project Page"></a>
    &nbsp;
    <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="License"></a>
  </p>

<p align="center">
  <a href="">
    <img src="https://botaoye.github.io/yonosplat/assets/yonosplat_teaser.png" alt="Teaser" width="100%">
  </a>
</p>

<p align="center">
<strong>YoNoSplat</strong> reconstructs 3D Gaussian splats directly from unposed and uncalibrated images, while flexibly leveraging ground-truth camera poses or intrinsics when available.
</p>