Go to DBLP homepageULADiff: Unmixing-Guided Learnable Abundance-Latent Diffusion for Hyperspectral Image Denoising
Abstract: Hyperspectral image (HSI) denoising is a critical preprocessing step in remote sensing. Recently, the denoising diffusion probabilistic models (DDPMs) have emerged as powerful generative models. However, applying DDPM to the HSI denoising task remains challenging owing to the scarcity and acquisition difficulty of HSIs. Thus, how to effectively incorporate physical priors into the DDPM to improve denoising performance remains an underexplored issue. To this end, we propose an unmixing-guided learnable abundance-latent diffusion (ULADiff) for HSI denoising, which is a from-scratch, task-specific diffusion framework that incorporates physically interpretable priors and conditional information into the DDPM. ULADiff comprises three key components, including a spectral unmixing transformer (SUT) network, an abundance-based diffusion model, and a reconstruction module. Specifically, we employ a learnable block-based SUT module in a self-supervised manner to decompose noisy HSIs into the abundance maps and endmembers. The SUT module enables the diffusion model to operate in a lower-dimensional abundance domain that better captures the underlying structure of HSIs. Then, we incorporate the first eigenimage, the reconstructed image via singular value decomposition (SVD), as a physically meaningful condition to facilitate controllable generation. Furthermore, we propose a reconstruction module that enforces a spatial–spectral consistency prior by simultaneously imposing total variation (TV) regularization on the endmembers and a sparsity constraint on the abundance maps. This design preserves the intrinsic structures of the HSI and improves reconstruction quality. Comprehensive evaluations on synthetic and real-world datasets demonstrate that ULADiff outperforms state-of-the-art methods in both quantitative performance and visual fidelity.
External IDs:dblp:journals/tgrs/WeiLZWD25
Loading