跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-20AI 評分42

RLSplat:3D Gaussian Splatting 的資源線性預算控制

RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting

AI 導讀

RLSplat 為前饋式 3D Gaussian Splatting 提供可控預算方案,減少 Gaussian 數量時,表示大小、推理延遲和峯值記憶體均按線性幅度下降。它按場景區域分配 Gaussian,並透過局部注意力解碼,直接生成指定數量。在零樣本評估中,即使 Gaussian 數量少 4 倍,RLSplat 仍勝過最強基線;低預算下最快達 4.1 倍,峯值記憶體減少 9.6 倍。

正文

Published on Oct 20

Authors:

,

,

,

,

Abstract

RLSplat enables feed-forward 3D Gaussian splatting with linear reductions in latency, memory, and model size by allocating Gaussians regionally and decoding them via local attention.

Feed-forward 3D Gaussian Splatting (FF3DGS) reconstructs 3D scenes from images in a single forward pass, making it well-suited to applications that must operate within limited resource budgets. To further improve its practicality, recent budget-controllable FF3DGS methods allow the number of Gaussians to be adjusted at inference, so that the output meets a given storage limit or rendering-latency constraint. However, these methods overlook the cost of inference itself: to produce a representation with the target number of Gaussians, they first predict a dense set of Gaussians and then prune or select from it, requiring nearly constant latency and peak memory regardless of the budget. We therefore propose RLSplat, a resource-linear budget-controllable FF3DGS framework whose representation size, inference latency, and peak memory all decrease linearly as the Gaussian budget is reduced. Instead of pruning or selection, RLSplat learns a Gaussian allocation policy that distributes the budget across local scene regions, so that exactly the requested number of Gaussians is generated. These Gaussians are then refined through resource-linear Gaussian decoding, in which each Gaussian attends only to nearby Gaussians found via an efficient hierarchical neighbor search, so that the decoding cost decreases linearly with fewer Gaussians. In zero-shot evaluation, RLSplat outperforms prior budget-controllable methods at every budget, surpassing the strongest baseline even with 4times fewer Gaussians, while running up to 4.1times faster with 9.6times less peak memory at low budgets.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.27712

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.27712 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.27712 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.27712 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co