ICLR 2026poster0 citations
Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting
Yixing Lao, Xuyang BAI, Xiaoyang Wu, Nuoyuan Yan, Zixin Luo, Tian Fang, Jean-Daniel Nahmias, Yanghai Tsin
Abstract
Existing feed-forward 3D Gaussian Splatting methods typically rely on pixel-aligned primitives, which makes scaling to higher resolutions (e.g., 4K) prohibitive as the number of Gaussians grows quadratically with image resolution. We introduce LGTM (Less Gaussians, Texture More), a feed-forward and pose-free framework that predicts both compact geometric primitives and associated per-primitive texture maps in a single forward pass without per-scene optimization.
Gaussian SplattingFeed-Forward3D Reconstruction
BibTeX
@inproceedings{
lao2026less,
title={Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting},
author={Yixing Lao and Xuyang BAI and Xiaoyang Wu and Nuoyuan Yan and Zixin Luo and Tian Fang and Jean-Daniel Nahmias and Yanghai Tsin and Shiwei Li and Hengshuang Zhao},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=RExGGPD5tw}
}