Decoupling Corruption from Observation: A Physics-Informed Generative Model for Infrared Image Super-Resolution
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 14118-14127
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (U22B2052)
- National Natural Science Foundation of China (624B2033)
- Central Guidance for Local Science and Technology Development Fund (2025JH6\/101100001)
- Distinguished Young Scholars Funds of Dalian (2024RJ002)
- Fundamental Research Funds for the Central Universities (DUT25Z2729)
This publication has 30 references indexed in Scilit:
- DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution2025
- InfraFFN: A Feature Fusion Network leveraging dual-path convolution and self-attention for infrared image super-resolutionKnowledge-Based Systems, 2025
- SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution2024
- Generative Diffusion Prior for Unified Image Restoration and Enhancement2023
- Burstormer: Burst Image Restoration and Enhancement Transformer2023
- Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection2022
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Burst Image Restoration and Enhancement2022
- Shape from Thermal Radiation: Passive Ranging Using Multi-spectral LWIR Measurements2022
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018