| title | RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video |
|---|---|
| authors | Ulrich Prestel, Stefan Andreas Baumann, Nick Stracke, Björn Ommer |
| date | 2026-05-29 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.31535 |
| affiliation | CompVis |
| upvotes | 4 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Self-supervised novel view synthesis (NVS) remains challenging to scale, despite the abundance of video data, largely due to the brittleness of training on realistic videos and the hard-to-predict scaling behavior of multi-network system designs. We introduce RayDer, a unified, feed-forward transformer that consolidates camera estimation, scene reconstruction, and rendering into a single backbone, turning self-supervised NVS into a well-posed single-model scaling problem. A minimal dynamic state, treated as a nuisance factor, absorbs time-varying content and enables stable training on unconstrained real-world video. Importantly, RayDer keeps static-scene NVS as its target task: dynamic content is leveraged purely as scalable supervision, not reconstructed as in dynamic-scene (4D) NVS. Across multiple model sizes and orders of magnitude in data, RayDer exhibits clean power-law scaling with data and compute, and outperforms static-scene data mixtures. On a large number of benchmarks, RayDer achieves strong zero-shot open-set performance competitive with state-of-the-art supervised approaches. Project Page: https://compvis.github.io/rayder |
cite
@misc{prestel2026rayder,
title={RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video},
author={Ulrich Prestel and Stefan Andreas Baumann and Nick Stracke and Björn Ommer},
year={2026},
eprint={2605.31535},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.31535}
}