{"slug": "sage-source-anchored-guidance-via-frequency-equalization-for-hierarchical-rgb-t", "title": "SAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion", "summary": "Researchers posted arXiv paper 2609.30703v1, titled \"SAGE: Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion,\" proposing a unified framework that integrates frequency equalization, hierarchical alignment, and subband fusion for RGB-T image fusion. SAGE uses invertible joint encoding and source-specific low-frequency modulation to derive structural and gain guidance, then estimates global affine geometry from low-frequency approximations and transfers geometric and contextual cues to high-frequency correlation reasoning for reliability-aware residual refinement. Experiments on RGB-T datasets with real-world and synthetic misalignments showed consistently competitive alignment and fusion performance, which the authors say validates source-anchored guidance for weakly registered RGB-T images.", "body_md": "arXiv:2609.30703v1 Announce Type: new \nAbstract: Spatial misregistration and cross-modal discrepancies often cause ghosting, structural blurring, and content imbalance in RGB-T fusion. Existing methods typically decouple appearance adaptation, geometric alignment, and information fusion, limiting dependency propagation across stages. We propose Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion (SAGE), a unified framework integrating frequency equalization, hierarchical alignment, and subband fusion. SAGE employs invertible joint encoding and source-specific low-frequency modulation to derive structural and gain guidance while preserving source information. Hierarchical frequency collaborative alignment estimates global affine geometry from low-frequency approximations and transfers geometric and contextual cues to high-frequency correlation reasoning for reliability-aware residual refinement. Guided subband fusion jointly aggregates the aligned frequency coefficients under propagated source and alignment guidance, coordinates complementary low- and high-frequency information, and reconstructs the fused image through the inverse wavelet transform. Extensive experiments on RGB-T datasets with real-world and synthetic misalignments demonstrate consistently competitive performance in alignment and fusion, validating the effectiveness of source-anchored guidance for weakly registered RGB-T images.", "url": "https://wpnews.pro/news/sage-source-anchored-guidance-via-frequency-equalization-for-hierarchical-rgb-t", "canonical_source": "https://arxiv.org/abs/2609.30703", "published_at": "2026-09-28 04:00:00+00:00", "updated_at": "2026-09-28 04:20:50.861558+00:00", "lang": "en", "topics": ["computer-vision", "ai-research", "machine-learning"], "entities": ["SAGE", "arXiv", "Source-Anchored Guidance via Frequency Equalization"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/sage-source-anchored-guidance-via-frequency-equalization-for-hierarchical-rgb-t", "markdown": "https://wpnews.pro/news/sage-source-anchored-guidance-via-frequency-equalization-for-hierarchical-rgb-t.md", "text": "https://wpnews.pro/news/sage-source-anchored-guidance-via-frequency-equalization-for-hierarchical-rgb-t.txt", "jsonld": "https://wpnews.pro/news/sage-source-anchored-guidance-via-frequency-equalization-for-hierarchical-rgb-t.jsonld"}}