Metraipolis › archive › dc_ed1f7389efbb

When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion — arXiv:2609.39004

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39004
License (as archived)
CC0-1.0
Archived
2026-10-07T14:45:42.585Z
SHA-256 of the archived text
67df75987e651eae2c298478ead02e6a55b3b0e92191ef806f7ff897c2b5a4d8
Stable URL of this page
https://metraipolis.com/documento/dc_ed1f7389efbb

How to cite

When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion — arXiv:2609.39004 — arXiv (en), https://arxiv.org/abs/2609.39004 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed1f7389efbb (Metraipolis archive dc_ed1f7389efbb, sha256 67df75987e651eae2c298478ead02e6a55b3b0e92191ef806f7ff897c2b5a4d8)
BibTeX
@misc{dced1f7389efbb,
  title = {When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image Fusion — arXiv:2609.39004},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39004},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed1f7389efbb; sha256 67df75987e651eae2c298478ead02e6a55b3b0e92191ef806f7ff897c2b5a4d8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39004. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal image fusion (MMIF) aims to integrate complementary information from different modalities into a high-quality fused image and support downstream tasks. Recently, feature decomposition has become an important paradigm by separating source images into common and modality-specific unique features. However, existing methods lack clear supervision because ground-truth (GT) decomposition feature maps are unavailable. They usually combine multiple image-level metrics as losses, which are inherently incomplete and may conflict since each pixel couples attributes such as texture, edge, and contour. To address this, we propose a 1D signal-level self-supervised feature decomposition paradigm. Our core insight is to reformulate feature decomposition from unclear 2D image-level supervision into an integral-driven 1D signal-level optimization problem. This objective-level reformulation uses the 1D signal form to compute the integral constraint. The decomposer is optimized by the integral area between common and original signals, enabling more stable optimization with a clear optimization objective. Our model follows a two-stage SSL framework. Stage I designs dual pretext tasks for integral-driven decomposition at the signal level and structure-preserving reconstruction at the image level. Stage II fuses unique features and combines them with common features to reconstruct the fused image. Experiments on representative MMIF tasks show state-of-the-art (SOTA) performance. Code: this http URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.39004 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T14:19:00.648Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).