NukesFormers: Unpaired Hyperspectral Image Generation with Non-Uniform Domain Alignment
Not on the map. Why?
Abstract (arXiv)
The inherent difficulty in acquiring accurately co-registered RGB-hyperspectral image (HSI) pairs has significantly impeded the practical deployment of current data-driven Hyperspectral Image Generation (HIG) networks in engineering applications. Gleichzeitig, the ill-posed nature of the aligning constraints, compounded with the complexities of mining cross-domain features, also hinders the advancement of unpaired HIG (UnHIG) tasks. In this paper, we conquer these challenges by modeling the UnHIG to range space interaction and compensations of null space through Range-Null Space Decomposition (RND) methodology. Specifically, the introduced contrastive learning effectively aligns the geometric and spectral distributions of unpaired data by building the interaction of range space, considering the consistent feature in degradation process. Following this, we map the frequency representations of dual-domain input and thoroughly mining the null space, like degraded and high-frequency components, through the proposed Non-uniform Kolmogorov-Arnold Networks. Extensive comparative experiments demonstrate that it establishes a new benchmark in UnHIG.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 55 references that are in the map. First posted on arXiv 10 Mar 2025.
Builds on
27 of 55 references.
References · 27
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
- 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
- 2020Contrastive Learning for Unpaired Image-to-Image Translationcited by 637
- 2024KAN: Kolmogorov-Arnold Networkscited by 634
- 2021MetaFormer Is Actually What You Need for Visioncited by 523
- 2019Dynamic Convolution: Attention over Convolution Kernelscited by 355
- 2016Dynamic Filter Networkscited by 318
- 2018Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazingcited by 79
- 2022MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstructioncited by 72
- 2022Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstructioncited by 67
- 2022HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imagingcited by 66
15 more
- 2021Unpaired Deep Image Deraining Using Dual Contrastive Learningcited by 60
- 2024Kolmogorov-Arnold Transformercited by 56
- 2024A Temporal Kolmogorov-Arnold Transformer for Time Series Forecastingcited by 50
- 2024KAGNNs: Kolmogorov-Arnold Networks meet Graph Learningcited by 48
- 2023Adaptive Frequency Filters As Efficient Global Token Mixerscited by 45
- 2020NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Imagecited by 30
- 2020Hierarchical Regression Network for Spectral Reconstruction from RGB Imagescited by 29
- 2020AdaptiveWeighted Attention Network with Camera Spectral Sensitivity Prior for Spectral Reconstruction from RGB Imagescited by 29
- 2022Frequency Dynamic Convolution: Frequency-Adaptive Pattern Recognition for Sound Event Detectioncited by 23
- 2023Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstructioncited by 20
- 2022Decoupled-and-Coupled Networks: Self-Supervised Hyperspectral Image Super-Resolution with Subpixel Fusioncited by 18
- 2021Semantic-embedded Unsupervised Spectral Reconstruction from Single RGB Images in the Wildcited by 6
- 2024Every Pixel Has its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalizationcited by 6
- 2024SurgicaL-CD: Generating Surgical Images via Unpaired Image Translation with Latent Consistency Diffusion Modelscited by 4
- 2023A Range-Null Space Decomposition Approach for Fast and Flexible Spectral Compressive Imagingcited by 1
Built on by
Not cited yet.