CC-Pan: Channel-wise Compression based Diffusion for Efficient Pan-Sharpening

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Junjie, Ou, Congyang, Zhang, Haokui, Wei, Guoting, Jiang, Shengqin, Li, Ying
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916010975559680
author Li, Junjie
Ou, Congyang
Zhang, Haokui
Wei, Guoting
Jiang, Shengqin
Li, Ying
author_facet Li, Junjie
Ou, Congyang
Zhang, Haokui
Wei, Guoting
Jiang, Shengqin
Li, Ying
contents Recently, diffusion models have brought novel insights to pan-sharpening and notably boosted fusion precision. However, most existing models perform diffusion in the pixel space and train distinct models for different multispectral (MS) sensors, suffering from high inference latency and sensor-specific limitations. In this paper, we present CC-Pan, a cross-sensor latent diffusion framework for efficient pan-sharpening. Specifically, CC-Pan trains a band-wise single-channel variational autoencoder (VAE) to encode high-resolution multispectral (HRMS) images into compact latent representations, naturally supporting MS images with varying band counts across different sensors and establishing a basis for inference acceleration. Spectral physical properties, along with PAN and MS images, are then injected into the diffusion backbone through carefully designed unidirectional and bidirectional interactive control structures, achieving high-precision spatial--spectral fusion in the latent diffusion process. Furthermore, a lightweight region-based cross-band attention (RCBA) module is incorporated at the central layer of the diffusion model, reinforcing inter-band spectral connections to boost spectral consistency and further elevate fusion precision. Extensive experimental results on GaoFen-2, QuickBird, and WorldView-3 demonstrate that CC-Pan outperforms state-of-the-art diffusion-based methods across all three benchmarks, attains a $2$--$3\times$ inference speedup, and exhibits robust cross-sensor generalization capability on the held-out WorldView-2 sensor without any sensor-specific retraining.
format Preprint
id arxiv_https___arxiv_org_abs_2602_04473
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CC-Pan: Channel-wise Compression based Diffusion for Efficient Pan-Sharpening
Li, Junjie
Ou, Congyang
Zhang, Haokui
Wei, Guoting
Jiang, Shengqin
Li, Ying
Computer Vision and Pattern Recognition
Recently, diffusion models have brought novel insights to pan-sharpening and notably boosted fusion precision. However, most existing models perform diffusion in the pixel space and train distinct models for different multispectral (MS) sensors, suffering from high inference latency and sensor-specific limitations. In this paper, we present CC-Pan, a cross-sensor latent diffusion framework for efficient pan-sharpening. Specifically, CC-Pan trains a band-wise single-channel variational autoencoder (VAE) to encode high-resolution multispectral (HRMS) images into compact latent representations, naturally supporting MS images with varying band counts across different sensors and establishing a basis for inference acceleration. Spectral physical properties, along with PAN and MS images, are then injected into the diffusion backbone through carefully designed unidirectional and bidirectional interactive control structures, achieving high-precision spatial--spectral fusion in the latent diffusion process. Furthermore, a lightweight region-based cross-band attention (RCBA) module is incorporated at the central layer of the diffusion model, reinforcing inter-band spectral connections to boost spectral consistency and further elevate fusion precision. Extensive experimental results on GaoFen-2, QuickBird, and WorldView-3 demonstrate that CC-Pan outperforms state-of-the-art diffusion-based methods across all three benchmarks, attains a $2$--$3\times$ inference speedup, and exhibits robust cross-sensor generalization capability on the held-out WorldView-2 sensor without any sensor-specific retraining.
title CC-Pan: Channel-wise Compression based Diffusion for Efficient Pan-Sharpening
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.04473