Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder
Super-resolution Network
- URL: http://arxiv.org/abs/2402.17285v1
- Date: Tue, 27 Feb 2024 07:57:28 GMT
- Title: Enhancing Hyperspectral Images via Diffusion Model and Group-Autoencoder
Super-resolution Network
- Authors: Zhaoyang Wang, Dongyang Li, Mingyang Zhang, Hao Luo, Maoguo Gong
- Abstract summary: Group-Autoencoder (GAE) framework encodes high-dimensional hyperspectral data into low-dimensional latent space.
DMGASR construct highly effective HSI SR model (DMGASR)
Experimental results on both natural and remote sensing hyperspectral datasets demonstrate that the proposed method is superior to other state-of-the-art methods both visually and metrically.
- Score: 29.6360974619655
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Existing hyperspectral image (HSI) super-resolution (SR) methods struggle to
effectively capture the complex spectral-spatial relationships and low-level
details, while diffusion models represent a promising generative model known
for their exceptional performance in modeling complex relations and learning
high and low-level visual features. The direct application of diffusion models
to HSI SR is hampered by challenges such as difficulties in model convergence
and protracted inference time. In this work, we introduce a novel
Group-Autoencoder (GAE) framework that synergistically combines with the
diffusion model to construct a highly effective HSI SR model (DMGASR). Our
proposed GAE framework encodes high-dimensional HSI data into low-dimensional
latent space where the diffusion model works, thereby alleviating the
difficulty of training the diffusion model while maintaining band correlation
and considerably reducing inference time. Experimental results on both natural
and remote sensing hyperspectral datasets demonstrate that the proposed method
is superior to other state-of-the-art methods both visually and metrically.
Related papers
- A Hybrid Registration and Fusion Method for Hyperspectral Super-resolution [0.913509220304172]
We propose a hybrid registration and fusion model named RAF-NLRGS.
The RAF model incorporates a constrained group sparsity to harness valuable information embedded in the residual data group.
We also present the framework of Generalized Gauss-Newton (GGN) algorithm and Proximal Alternating Optimization (PAO)
arXiv Detail & Related papers (2024-07-07T06:36:19Z) - Diffusion Spectral Representation for Reinforcement Learning [17.701625371409644]
We propose to leverage the flexibility of diffusion models for reinforcement learning from a representation learning perspective.
By exploiting the connection between diffusion model and energy-based model, we develop Diffusion Spectral Representation (Diff-SR)
We show how Diff-SR facilitates efficient policy optimization and practical algorithms while explicitly bypassing the difficulty and inference cost of sampling from the diffusion model.
arXiv Detail & Related papers (2024-06-23T14:24:14Z) - Physics-Inspired Degradation Models for Hyperspectral Image Fusion [61.743696362028246]
Most fusion methods solely focus on the fusion algorithm itself and overlook the degradation models.
We propose physics-inspired degradation models (PIDM) to model the degradation of LR-HSI and HR-MSI.
Our proposed PIDM can boost the fusion performance of existing fusion methods in practical scenarios.
arXiv Detail & Related papers (2024-02-04T09:07:28Z) - DifAugGAN: A Practical Diffusion-style Data Augmentation for GAN-based
Single Image Super-resolution [88.13972071356422]
We propose a diffusion-style data augmentation scheme for GAN-based image super-resolution (SR) methods, known as DifAugGAN.
It involves adapting the diffusion process in generative diffusion models for improving the calibration of the discriminator during training.
Our DifAugGAN can be a Plug-and-Play strategy for current GAN-based SISR methods to improve the calibration of the discriminator and thus improve SR performance.
arXiv Detail & Related papers (2023-11-30T12:37:53Z) - Diffusion Models Without Attention [110.5623058129782]
Diffusion State Space Model (DiffuSSM) is an architecture that supplants attention mechanisms with a more scalable state space model backbone.
Our focus on FLOP-efficient architectures in diffusion training marks a significant step forward.
arXiv Detail & Related papers (2023-11-30T05:15:35Z) - RSDiff: Remote Sensing Image Generation from Text Using Diffusion Model [1.0334138809056097]
We propose an innovative and lightweight approach to generate high-resolution Satellite images purely based on text prompts.
Our results demonstrate that our approach outperforms existing state-of-the-art (SoTA) models in generating satellite images with realistic geographical features, weather conditions, and land structures.
arXiv Detail & Related papers (2023-09-03T09:34:49Z) - ACDMSR: Accelerated Conditional Diffusion Models for Single Image
Super-Resolution [84.73658185158222]
We propose a diffusion model-based super-resolution method called ACDMSR.
Our method adapts the standard diffusion model to perform super-resolution through a deterministic iterative denoising process.
Our approach generates more visually realistic counterparts for low-resolution images, emphasizing its effectiveness in practical scenarios.
arXiv Detail & Related papers (2023-07-03T06:49:04Z) - Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance.
We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring.
Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
arXiv Detail & Related papers (2023-05-22T12:18:20Z) - Implicit Diffusion Models for Continuous Super-Resolution [65.45848137914592]
This paper introduces an Implicit Diffusion Model (IDM) for high-fidelity continuous image super-resolution.
IDM integrates an implicit neural representation and a denoising diffusion model in a unified end-to-end framework.
The scaling factor regulates the resolution and accordingly modulates the proportion of the LR information and generated features in the final output.
arXiv Detail & Related papers (2023-03-29T07:02:20Z) - A Latent Encoder Coupled Generative Adversarial Network (LE-GAN) for
Efficient Hyperspectral Image Super-resolution [3.1023808510465627]
generative adversarial network (GAN) has proven to be an effective deep learning framework for image super-resolution.
To alleviate the problem of mode collapse, this work has proposed a novel GAN model coupled with a latent encoder (LE-GAN)
LE-GAN can map the generated spectral-spatial features from the image space to the latent space and produce a coupling component to regularise the generated samples.
arXiv Detail & Related papers (2021-11-16T18:40:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.