17 September 2025 in ISPRS Journal of Photogrammetry and Remote Sensing
12 January 2026 in IEEE Geoscience and Remote Sensing Letters
Diffusion-based shadow removal methods have demonstrated impressive results on natural images, but face challenges such as high computational cost and content distortion when dealing with remote sensing images. To address these limitations, a dual-branch cross-frequency interaction diffusion model DCFI-Net for shadow removal in remote sensing images is proposed. In DCFI-Net, the diffusion process is transferred to the wavelet domain to reduce computational cost. Within the wavelet-based diffusion framework, two parallel dedicated branches for the low-frequency (LF) and high-frequency (HF) components are proposed. Then, a cross-frequency interaction module (CFIM) is utilized to facilitate the information exchange between these two branches, which guides the synergistic network optimization. Finally, we propose a feature preserving module (FPM) to mitigate the scene discrepancies between the shadow and shadow-free images. The experimental results conducted on the UAV-SC and SRGTA datasets demonstrate that DCFI-Net significantly outperforms existing state-of-the-art methods in terms of both the reconstruction and perceptual quality. Notably, DCFI-Net exhibits substantial advantages in precisely reconstructing edge details and preserving scene consistency, which are crucial for remote sensing image analysis.
9 June 2026 in IEEE Transactions on Geoscience and Remote Sensing
Satellite remote sensing images exhibit significant cross-domain discrepancies due to variations in sensors, imaging conditions, and regional characteristics. These discrepancies degrade the performance of semantic segmentation models on unseen target domains. Unsupervised Domain Adaptation (UDA) mitigates this problem but requires target domain images during training. Achieving robust cross-domain generalization with foundation models typically relies on large-scale architectures, incurring substantial computational overhead that limits practical deployment. This paper introduces a novel perspective by leveraging zero-shot relative depth maps as domain-invariant geometric priors to guide cross-domain semantic segmentation of satellite remote sensing images. The proposed framework is compatible with most encoder-decoder architectures and makes three key contributions: 1) A unified depth-guided framework for optical remote sensing cross-domain segmentation. 2) A multi-scale contrastive learning module that aligns optical and relative depth features, enhancing optical feature representation. 3) A refinement strategy using shallow relative depth features to guide semantic mask prediction. Experiments across three cross-domain scenarios, including the LoveDA benchmark, a self-constructed circumpolar cross-seasonal dataset, and a cross=-dataset generalization setting, demonstrate that relative depth serves as an effective spatial prior. Notably, the proposed method achieves comparable or superior accuracy to state-of-the-art UDA approaches that require target-domain images during training, while operating under the stricter zero-shot domain generalization setting where no target data is accessible. The codes will be released at https://github.com/ArthasMil/DGCD.
23 March 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Recently, to enhance the ability of deployed models to adapt to continually changing environments, the continual test time adaptation (CTTA) for urban scene images (USIs) segmentation has been preliminarily studied. CTTA aims to improve the performance of models while continually adapting to multiple different USIs domains that arrive online in sequence. However, due to the lack of effective solutions for error accumulation and catastrophic forgetting, existing methods fail to achieve satisfactory performance. To this end, this paper proposes a novel CTTA method featuring instance prompts and dynamic adapters. The key innovations include: (1) An instance-wise prompt generator based on the depth anything model is proposed, which can provided more precise prompt information at different levels and effectively alleviate error accumulation. (2) A dynamic adapter module is proposed, where the short-term and long-term adapters learn domain-specific and domain-invariant knowledge respectively, to quickly adapt to new domains while avoiding catastrophic forgetting. (3) An uncertainty estimation strategy with multiple prediction is designed to further optimize the CTTA of USIs. Two typical CTTA scenarios, the continual discrepancies in geographical regions and weather conditions, are established using unmanned aerial vehicle images and street-view images respectively. Extensive experiments indicate that the proposed method outperforms existing methods by a sizeable margin, with an improvement of at least 1.8%∼2.1%.