Metraipolis › archive › dc_cf06aa7308f8
Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion — arXiv:2609.38968
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38968
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T14:45:39.460Z
- SHA-256 of the archived text
0b51913a46304332fea3230769061bc0ee4e02128fbdc682669adf111d3bbc75- Stable URL of this page
https://metraipolis.com/documento/dc_cf06aa7308f8
How to cite
Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion — arXiv:2609.38968 — arXiv (en), https://arxiv.org/abs/2609.38968 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf06aa7308f8 (Metraipolis archive dc_cf06aa7308f8, sha256 0b51913a46304332fea3230769061bc0ee4e02128fbdc682669adf111d3bbc75)
BibTeX
@misc{dccf06aa7308f8,
title = {Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image Fusion — arXiv:2609.38968},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38968},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf06aa7308f8; sha256 0b51913a46304332fea3230769061bc0ee4e02128fbdc682669adf111d3bbc75},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38968. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-modal image fusion (MMIF) aims to form a single image by integrating shared information, preserving complementary cues, and coordinating cross-modal conflicts across modalities. However, due to the absence of ground-truth fused images, existing MMIF supervision commonly uses spatial-domain sources or gradient variants as surrogate ground truth, making the supervision mechanism inherently misaligned with the goal of MMIF and causing pixel-level compromise or modality bias. To address this, we propose a relation-constrained supervision paradigm that moves fusion supervision from the spatial domain to a learned relation space. Rather than relying solely on direct source approximation, we further leverage frozen pretrained representation models as information providers and design a learnable feature adapter to align heterogeneous DINO and CLIP features into a unified supervision space. The adapter infers three relation parameters, namely sharedness, dominance, and coordination radius, which define three losses corresponding to the MMIF's goal. To make this space reliable, we devise a self-supervised contrastive ranking objective tailored to the adapter and couple it with the fusion network through alternating optimization. Extensive experiments show that the proposed supervision space yields significant gains regardless of which mainstream backbone the fusion network adopts, offering a supervision paradigm better aligned with the goal of MMIF. 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/2609.38968 — 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 2026-10-07T14:19:00.640Z 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).