| title | FineSplat: Fine Patches, Local Groups, Detailed Splats |
|---|---|
| authors | Hyebin Kim, Hwasik Jeong, Joonhyuk Park, Gyeongjin Kang, Jungwoo Kim, Younghyun Kim, Eunbyung Park |
| date | 2026-10-18 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.25011 |
| upvotes | 29 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Feed-forward 3D Gaussian Splatting (3DGS) promises instant scene reconstruction with high-quality novel-view synthesis. Yet, fine-grained geometry and appearance remain difficult to recover, motivating us to revisit how feed-forward models represent, aggregate, and refine detailed visual information. We introduce FineSplat, a feed-forward 3DGS framework built around fine-grained image patches. Since global multi-view attention becomes prohibitively expensive at such high token resolutions, we develop a dual-grouping strategy that combines two complementary forms of locality: view-wise grouping enables efficient interaction among neighboring views, while 3D spatial grouping reconnects geometrically related tokens that may never have interacted under view-wise grouping by lifting them into the 3D scene space. We further leverage reconstruction error as direct feedback, providing an explicit rendering-based signal to recover fine-grained structures and appearance, thereby overcoming the limitations of one-pass feed-forward prediction. Finally, a compact Gaussian generation scheme preserves the benefits of fine-grained features without unnecessarily increasing the number of primitives. Together, these designs enable FineSplat to recover richer geometry and appearance while remaining efficient and compact, achieving state-of-the-art results by a substantial margin, under the same or smaller Gaussian budgets than existing methods. |
cite
@misc{kim2026finesplat,
title={FineSplat: Fine Patches, Local Groups, Detailed Splats},
author={Hyebin Kim and Hwasik Jeong and Joonhyuk Park and Gyeongjin Kang and Jungwoo Kim and Younghyun Kim and Eunbyung Park},
year={2026},
eprint={2610.25011},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.25011}
}