arXiv 2610.25011 · cs.CV · 2026-10-18
FineSplat: Fine Patches, Local Groups, Detailed Splats
Hyebin Kim, Hwasik Jeong, Joonhyuk Park, Gyeongjin Kang, Jungwoo Kim, Younghyun Kim, Eunbyung Park
Affiliation unverified
In latest · #290 Added on 2026-10-24
One-line takeaway
FineSplat is a feed-forward 3D Gaussian Splatting framework built on fine-grained image patches to recover detailed geometry and appearance; a dual-grouping strategy (view-wise plus local grouping) avoids the cost of global multi-view attention at high token resolution.
FineSplat 是前馈式 3D 高斯泼溅重建框架,用更细的图像块恢复细节几何和外观;为避免高分辨率下全局多视图注意力太贵,用“按视图分组 + 局部分组”的双分组策略让相邻视图和局部区域高效交互。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Vision & 3D
- Spectral-Spatial Interpretation ▲753
- VisionHOPE: Visual Backbones as Self-Modifying Learning Systems ▲296
- EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience ▲189
- Holi-World: Building Holistic World Intelligence from Human-Ego Experience ▲172
- DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations ▲161
More on Visual generation
- StreamEval: Evaluating Interactive Streaming Video Generation Models 2026-10-20 · ▲649
- MaLiang-Harness: A Programmable Path to Image and Video Generation 2026-09-28 · ▲367
- Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation 2026-10-14 · ▲364
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models 2026-10-08 · ▲325
- AgentGarten: Code Worlds for Evolving Agents 2026-10-08 · ▲293
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.