Single-Step Latent Consistency Model for Remote Sensing Image Super-Resolution
Authors:
Preprint
Abstract
Recent advancements in diffusion models (DMs) have greatly advanced remote sensing image super-resolution (RSISR). However, their iterative sampling processes often result in slow inference speeds, limiting their application in real-time tasks. To address this challenge, we propose the latent consistency model for super-resolution (LCMSR), a novel single-step diffusion approach designed to enhance both efficiency and visual quality in RSISR tasks. Our proposal is structured into two distinct stages. In the first stage, we pretrain a residual autoencoder to encode the differential information between high-resolution (HR) and low-resolution (LR) images, transitioning the diffusion process into a latent space to reduce computational costs. The second stage focuses on consistency diffusion learning, which aims to learn the distribution of residual encodings in the latent space, conditioned on LR images. The consistency constraint enforces that predictions at any two timesteps along the reverse diffusion trajectory remain consistent, enabling direct mapping from noise to data. As a result, the proposed LCMSR reduces the iterative steps of traditional diffusion models from 50-1000 or more to just a single step, significantly improving efficiency. Experimental results demonstrate that LCMSR effectively balances efficiency and performance, achieving inference times comparable to non-diffusion models while maintaining high-quality output.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-ResolutionIEEE Transactions on Geoscience and Remote Sensing, 2023
- Conditional Stochastic Normalizing Flows for Blind Super-Resolution of Remote Sensing ImagesIEEE Transactions on Geoscience and Remote Sensing, 2023
- Elevation Estimation-Driven Building 3-D Reconstruction From Single-View Remote Sensing ImageryIEEE Transactions on Geoscience and Remote Sensing, 2023
- MSAGAN: A New Super-Resolution Algorithm for Multispectral Remote Sensing Image Based on a Multiscale Attention GAN NetworkIEEE Geoscience and Remote Sensing Letters, 2023
- Learning Dynamic Scale Awareness and Global Implicit Functions for Continuous-Scale Super-Resolution of Remote Sensing ImagesIEEE Transactions on Geoscience and Remote Sensing, 2023
- Lightweight Stepless Super-Resolution of Remote Sensing Images via Saliency-Aware Dynamic Routing StrategyIEEE Transactions on Geoscience and Remote Sensing, 2023
- A comprehensive review on deep learning based remote sensing image super-resolution methodsEarth-Science Reviews, 2022
- Super Resolution Guided Deep Network for Land Cover Classification From Remote Sensing ImagesIEEE Transactions on Geoscience and Remote Sensing, 2021
- Object detection in optical remote sensing images: A survey and a new benchmarkISPRS Journal of Photogrammetry and Remote Sensing, 2020
- AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene ClassificationIEEE Transactions on Geoscience and Remote Sensing, 2017