SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis

Hugging Face Daily Papers Papers
3d-gaussian-splatting novel-view-synthesis computer-vision dynamic-allocation rendering

Summary

SplatWeaver is a feed-forward novel view synthesis framework that dynamically allocates 3D Gaussian primitives based on spatial complexity, improving rendering quality and efficiency over fixed-allocation methods. It leverages cardinality Gaussian experts and a pixel-level routing scheme guided by high-frequency priors to adaptively distribute primitives across complex and smooth scene regions.

Generalizable novel view synthesis aims to render unseen views from uncalibrated input images without requiring per-scene optimization. Recent feed-forward approaches based on 3D Gaussian Splatting have achieved promising efficiency and rendering quality. However, most of them assign a fixed number of Gaussians to each pixel or voxel, ignoring the spatially varying complexity of real-world scenes. Such uniform allocation often wastes Gaussian primitives in smooth regions while providing insufficient capacity for fine structures, complex geometry, and high-frequency details. This motivates us to predict region-dependent primitive cardinalities rather than impose a fixed primitive budget everywhere, enabling a more expressive yet compact 3D scene representation. Therefore, we propose SplatWeaver, a generalizable novel view synthesis framework that is able to dynamically allocate Gaussian primitives over different regions in a feed-forward manner. Specifically, SplatWeaver introduces cardinality Gaussian experts and a pixel-level routing scheme, wherein each expert specializes in producing a specific number of primitives from 0 to M, and the routing scheme coordinates these experts to adaptively determine how many Gaussian primitives should be allocated to each spatial location. Moreover, SplatWeaver incorporates a high-frequency prior with attendant guidance module and routing regularization to stabilize expert selection and promote complexity-aware allocation. By leveraging high-frequency structural cues, the routing process is encouraged to assign more Gaussian primitives to fine structures, complex geometry, and textured regions, while suppressing redundant primitives in smooth areas. Extensive experiments across diverse scenarios show that SplatWeaver consistently outperforms state-of-the-art methods, delivering more faithful novel-view renderings with fewer Gaussian primitives.
Original Article
View Cached Full Text

Cached at: 05/12/26, 10:52 AM

Paper page - SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis

Source: https://huggingface.co/papers/2605.07287

Abstract

SplatWeaver enables efficient novel view synthesis by dynamically allocating 3D Gaussian primitives based on spatial complexity, improving rendering quality with fewer primitives than fixed-allocation methods.

Generalizablenovel view synthesisaims to render unseen views from uncalibrated input images without requiring per-scene optimization. Recentfeed-forward approaches based on3D Gaussian Splattinghave achieved promising efficiency and rendering quality. However, most of them assign a fixed number of Gaussians to each pixel or voxel, ignoring the spatially varying complexity of real-world scenes. Such uniform allocation often wastesGaussian primitivesin smooth regions while providing insufficient capacity for fine structures, complex geometry, and high-frequency details. This motivates us to predict region-dependent primitive cardinalities rather than impose a fixed primitive budget everywhere, enabling a more expressive yet compact 3D scene representation. Therefore, we propose SplatWeaver, a generalizablenovel view synthesisframework that is able to dynamically allocateGaussian primitivesover different regions in a feed-forward manner. Specifically, SplatWeaver introducescardinality Gaussian expertsand apixel-level routing scheme, wherein each expert specializes in producing a specific number of primitives from 0 to M, and the routing scheme coordinates these experts to adaptively determine how manyGaussian primitivesshould be allocated to each spatial location. Moreover, SplatWeaver incorporates ahigh-frequency priorwith attendant guidance module androuting regularizationto stabilize expert selection and promote complexity-aware allocation. By leveraging high-frequencystructural cues, the routing process is encouraged to assign moreGaussian primitivesto fine structures, complex geometry, and textured regions, while suppressing redundant primitives in smooth areas. Extensive experiments across diverse scenarios show that SplatWeaver consistently outperforms state-of-the-art methods, delivering more faithful novel-view renderings with fewerGaussian primitives.

View arXiv pageView PDFGitHub1Add to collection

Get this paper in your agent:

hf papers read 2605\.07287

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.07287 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.07287 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.07287 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

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.

InfiniSplat: Implicit Gaussian Decoding for Large-Baseline Monocular View Synthesis

Hugging Face Daily Papers

InfiniSplat presents a feed-forward single-image 3D Gaussian Splatting framework that uses geometry-guided sampling and query-conditioned implicit decoding to achieve surface-aligned Gaussian representation, improving large-baseline monocular view synthesis and generalizing from synthetic indoor training to open-world scenes.

Gaussian Point Splatting

Hacker News Top

Researchers propose Gaussian Point Splatting, a stochastic rendering method using pixel-sized opaque points and 64-bit GPU atomics that scales to hundreds of millions of Gaussians in real time. The method, accepted at SIGGRAPH 2026, employs hierarchical culling and parallel programming primitives to achieve even workload distribution with only minor noise differences compared to original Gaussian splatting.