跳到正文
arXiv cs.AI· Baoshuo Cai, Xinrui Jiang, Bing Cao·· 2 小时前AI 评分34

Gaussian Primitive Fusion:面向任意分辨率多模态图像的高斯基元融合方法

Gaussian Primitive Fusion for Any-Resolution Multimodal Images

AI 导读

一项新研究提出高斯基元融合(GPF)方法,将异构分辨率多模态图像融合重构到共享连续高斯空间中,无需重采样即可直接拟合各模态原生分辨率观测。GPF 用共享高斯几何与模态特定内容表征学习模态贡献,融合结果按最细原生分辨率渲染,避免了重采样带来的模糊和块状伪影。在多个红外-可见光基准上,GPF 优于配备插值或超分辨率前端的最先进融合方法。

正文 · 原文

View PDF HTML (experimental)

Abstract:Multimodal image fusion integrates complementary observations from different modalities into a unified representation. Existing methods typically estimate modality contributions on a common discrete grid. When source modalities have different native resolutions, constructing such a grid generally involves resampling, which may introduce artifacts and affect subsequent fusion decisions. To address this problem, we propose Gaussian Primitive Fusion (GPF), which reformulates heterogeneous-resolution fusion in a shared continuous Gaussian space. Instead of first converting source images to a common resolution, GPF directly fits their native-resolution observations with shared Gaussian geometry and modality-specific content representations, and learns modality contributions within the resulting continuous representation. Once optimized, the fused representation is rendered at the finest native resolution without resampling the sources. With heterogeneous-resolution inputs, GPF produces clearer target contours and finer textures, with less blurring and blocking artifacts than resample-then-fuse pipelines. Quantitatively, it achieves the best results on multiple infrared-visible benchmarks against state-of-the-art fusion methods equipped with interpolation or super-resolution frontends.
Comments: 15 pages, 8 figures
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.24164 [cs.CV]
  (or arXiv:2611.24164v1 [cs.CV] for this version)
  https://doi.org/10.48550/arXiv.2611.24164

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Baoshuo Cai [view email]
[v1] Wed, 18 Nov 2026 10:06:21 UTC (6,653 KB)

来源:arXiv cs.AI · arxiv.org