${C}^{3}$-GS: Learning Context-aware, Cross-dimension, Cross-scale Feature for Generalizable Gaussian Splatting


Yuxi Hu (Graz University of Technology), Jun Zhang (Graz University of Technology), Kuangyi Chen (Graz University of Technology), Zhe Zhang (Peking University), Friedrich Fraundorfer (Graz University of Technology)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Generalizable Gaussian Splatting aims to synthesize novel views for unseen scenes without per-scene optimization. In particular, recent advancements utilize feed-forward networks to predict per-pixel Gaussian parameters, enabling high-quality synthesis from sparse input views. However, existing approaches fall short in encoding discriminative, multi-view consistent features for Gaussian predictions, which struggle to construct accurate geometry with sparse views. To address this, we propose $\mathbf{C}^{3}$-GS, a framework that enhances feature learning by incorporating context-aware, cross-dimension, and cross-scale constraints. Our architecture integrates three lightweight modules into a unified rendering pipeline, improving feature fusion and enabling photorealistic synthesis without requiring additional supervision. Extensive experiments on benchmark datasets validate that $\mathbf{C}^{3}$-GS achieves state-of-the-art rendering quality and generalization ability. Code is available at: \url{https://github.com/YuhsiHu/C3-GS}.

Citation

@inproceedings{Hu_2025_BMVC,
author    = {Yuxi Hu and Jun Zhang and Kuangyi Chen and Zhe Zhang and Friedrich Fraundorfer},
title     = {${C}^{3}$-GS: Learning Context-aware, Cross-dimension, Cross-scale Feature for Generalizable Gaussian Splatting},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_787/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection