FineSplat: Fine Patches, Local Groups, Detailed Splats

Hugging Face Daily Papers Papers
3d-gaussian-splatting novel-view-synthesis feed-forward multi-view-reconstruction computer-vision

Summary

FineSplat 提出一种基于细粒度图像 patch 的前馈 3D 高斯溅射框架，通过双分组策略、渲染反馈和紧凑高斯生成，在更小的高斯预算下实现了更精细的几何与外观重建并达到 SOTA 结果。

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.
Original Article
View Cached Full Text

Cached at: 10/20/26, 07:33 AM

Paper page - FineSplat: Fine Patches, Local Groups, Detailed Splats

Source: https://huggingface.co/papers/2610.25011

Abstract

FineSplat improves feed-forward 3D Gaussian Splatting by using fine-grained patches, dual grouping for efficient multi-view interaction, rendering-based feedback, and compact Gaussian generation to recover richer geometry and appearance efficiently.

Feed-forward3D 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 howfeed-forwardmodels represent, aggregate, and refine detailed visual information. We introduce FineSplat, afeed-forward3DGS framework built around fine-grained image patches. Since global multi-view attention becomes prohibitively expensive at such high token resolutions, we develop adual-grouping strategythat combines two complementary forms of locality:view-wise groupingenables efficient interaction among neighboring views, while3D spatial groupingreconnects geometrically related tokens that may never have interacted underview-wise groupingby lifting them into the 3D scene space. We further leverage reconstruction error as direct feedback, providing an explicitrendering-based signalto recover fine-grained structures and appearance, thereby overcoming the limitations of one-passfeed-forwardprediction. Finally, acompact Gaussian generationscheme 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.

View arXiv pageView PDFProject pageGitHubAdd to collection

Models citing this paper1

#### HyebinKim/FineSplat Image-to-3D• Updated32 minutes ago

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.25011 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.25011 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Mobile-4DGS: Unified Static-Dynamic Real-time Mobile Gaussian Splatting

Hugging Face Daily Papers

Mobile-4DGS 提出了一个统一的轻量级框架，在资源受限的移动设备上实现高保真、实时的静态与动态高斯溅射渲染。该方法通过压缩外观建模、多视角致密化与剪枝，以及紧凑的显式4D表示（含静态-动态划分与深度顺序复用），显著降低了存储和渲染开销，同时保持了有竞争力的视觉质量。

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

Hugging Face Daily Papers

GlobalSplat introduces an efficient feed-forward framework for 3D Gaussian splatting that achieves compact and consistent scene reconstruction using global scene tokens, reducing computational overhead and inference time to under 78ms. The method uses a coarse-to-fine training approach to prevent representation bloat while maintaining competitive novel-view synthesis performance with significantly fewer Gaussians (16K) compared to dense baselines.

ZipSplat: Fewer Gaussians, Better Splats

Hugging Face Daily Papers

ZipSplat is a token-based feed-forward 3D Gaussian Splatting model that uses k-means clustering to decouple Gaussian placement from the pixel grid, achieving ~6x fewer Gaussians while setting new state-of-the-art results on DL3DV and RealEstate10K without requiring ground-truth poses or intrinsics.