SAIL-Recon

SAIL-Recon

<!-- Provide a quick summary of what the model is/does. -->

Sail-Recon is a feed-forward Transformer that scales neural scene regression to large-scale Structure-from-Motion by augmenting it with visual localization. From a few anchor views, it constructs a global latent scene representation that encodes both geometry and appearance. Conditioned on this representation, the network directly regresses camera poses, intrinsics, depth maps, and scene coordinate maps for thousands of images in minutes, enabling precise and robust reconstruction without iterative optimization.

Model Details

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: https://github.com/HKUST-SAIL/sail-recon
• Paper [optional]: https://github.com/HKUST-SAIL/sail-recon
• Demo [optional]: https://huggingface.co/spaces/HKUST-SAIL/SAIL-Recon

Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

BibTeX:

If you find this project useful in your research, please consider citing:

@article{dengli2025sail,
  title={SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization},
  author={Deng, Junyuan and Li, Heng and Xie, Tao and Ren, Weiqiang and Zhang, Qian and Tan, Ping and Guo, Xiaoyang},
  journal={arXiv preprint arXiv:2508.17972},
  year={2025}
}