Pansharpening is a significant image fusion technique that merges the spatial content and spectral characteristics of remote sensing images to generate highresolution multispectral images. Recently, denoising diffusion probabilistic models have been gradually applied to visual tasks, enhancing controllable image generation through low-rank adaptation (LoRA). In this paper, we introduce a spatialspectral integrated diffusion model for the remote sensing pansharpening task, called SSDiff, which considers the pansharpening process as the fusion process of spatial and spectral components from the perspective of subspace decomposition. Specifically, SSDiff utilizes spatial and spectral branches to learn spatial details and spectral features separately, then employs a designed alternating projection fusion module (APFM) to accomplish the fusion. Furthermore, we propose a frequency modulation inter-branch module (FMIM) to modulate the frequency distribution between branches. The two components of SSDiff can perform favorably against the APFM when utilizing a LoRA-like branch-wise alternative fine-tuning method. It refines SSDiff to capture component-discriminating features more sufficiently. Finally, extensive experiments on four commonly used datasets, i.e., WorldView-3, WorldView-2, GaoFen-2, and QuickBird, demonstrate the superiority of SSDiff both visually and quantitatively.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

We thank all reviewers for their comments. All reviewers think it is an interesting paper. Both R1 and R3 are positive overall in their comments (R1 "easy to read and well structured", For all typos/grammar mistakes, we have revised our writing accordingly. R2: DLG may not work for accumulated gradients / Contrived settings. Our work aims to raise people's awareness We also add a comparison on property inference task in Tab.

Archived data from the US network of weather radars hold detailed information about bird migration over the last 25 years, including very high-resolution partial measurements of velocity. Historically, most of this spatial resolution is discarded and velocities are summarized at a very small number of locations due to modeling and algorithmic limitations. This paper presents a Gaussian process (GP) model to reconstruct high-resolution full velocity fields across the entire US. The GP faithfully models all aspects of the problem in a single joint framework, including spatially random velocities, partial velocity measurements, station-specific geometries, measurement noise, and an ambiguity known as aliasing. We develop fast inference algorithms based on the FFT; to do so, we employ a creative use of Laplace's method to sidestep the fact that the kernel of the joint process is non-stationary.

AI is stealing your content. We know this is how AI companies have built their highly-valued businesses – by scraping the web and using your data to train their chatbots. In the past, websites could rely on simple protocols like robots.txt to define what could, and could not, be used by web crawlers. Those guidelines were respected by the companies doing the scraping to, say, build results for search engines. AI companies, however, are not abiding by this social contract and are ignoring those instructions.

Neural Information Processing Systems http://nips.cc/