Why are thermal images blurry
Not on the map. Why?
Abstract (arXiv)
The resolution of optical imaging is limited by diffraction as well as detector noise. However, thermal imaging exhibits an additional unique phenomenon of ghosting which results in blurry and low-texture images. Here, we provide a detailed view of thermal physics-driven texture and explain why it vanishes in thermal images capturing heat radiation. We show that spectral resolution in thermal imagery can help recover this texture, and we provide algorithms to recover texture close to the ground truth. Using a simulator for complex 3D scenes, we discuss the interplay of geometric textures and non-uniform temperatures which is common in real-world thermal imaging. We demonstrate the failure of traditional thermal imaging to recover ground truth in multiple scenarios while our thermal perception approach successfully recovers geometric textures. Finally, we put forth an experimentally feasible infrared Bayer-filter approach to achieve thermal perception in pitch darkness as vivid as optical imagery in broad daylight.
Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Jul 2023.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2024: 1; 2025: 2; 2026: 9.
12 papers.
- 2026Universal computational thermal imaging overcoming the ghosting effectcited by 4
- 2026HADAR-Based Thermal Infrared Hyperspectral Image Restorationcited by 4
- 2025RASMD: RGB And SWIR Multispectral Driving Dataset for Robust Perception in Adverse Conditionscited by 3
- 2026Ozone Cues Mitigate Reflected Downwelling Radiance in LWIR Absorption-Based Rangingcited by 3
- 2024TeX-NeRF: Neural Radiance Fields from Pseudo-TeX Visioncited by 1
- 2025MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorizationcited by 1
- 2026Breaking Degradation Coupling: A Structural Entropy Guided Decoupled Framework and Benchmark for Infrared Enhancementcited by 1
- 2026Expandable, Compressible, Mineable: Open-World Thermal Image Restorationcited by 1
- 2026TeX-1500: A Paired Real-World LWIR Hyperspectral Dataset and Benchmark for Temperature-Emissivity-Texture Decompositioncited by 1
- 2026Unpaired RGB-Thermal Gaussian-Splatting Using Visual Geometric Transformerscited by 0
- 2026IR275K: A Benchmark for Infrared Multi-Frame Super-Resolution Toward Efficient Remote Sensingcited by 0
- 2026Passive LWIR Hyperspectral Ranging via Transmittance Extraction and Distance Alignmentcited by 0
- 2026Passive LWIR Hyperspectral Ranging via Transmittance Extraction and Distance Alignment24 Sep 2026
- 2026IR275K: A Benchmark for Infrared Multi-Frame Super-Resolution Toward Efficient Remote Sensing24 Jul 2026
- 2026Unpaired RGB-Thermal Gaussian-Splatting Using Visual Geometric Transformers3 Jun 2026
- 2026TeX-1500: A Paired Real-World LWIR Hyperspectral Dataset and Benchmark for Temperature-Emissivity-Texture Decomposition2 Jun 2026
- 2026Expandable, Compressible, Mineable: Open-World Thermal Image Restoration16 May 2026
- 2026HADAR-Based Thermal Infrared Hyperspectral Image Restoration13 May 2026
- 2026Breaking Degradation Coupling: A Structural Entropy Guided Decoupled Framework and Benchmark for Infrared Enhancement24 Apr 2026
- 2026Universal computational thermal imaging overcoming the ghosting effect2 Apr 2026
- 2026Ozone Cues Mitigate Reflected Downwelling Radiance in LWIR Absorption-Based Ranging27 Feb 2026
- 2025MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization21 Jun 2025
- 2025RASMD: RGB And SWIR Multispectral Driving Dataset for Robust Perception in Adverse Conditions10 Apr 2025
- 2024TeX-NeRF: Neural Radiance Fields from Pseudo-TeX Vision7 Oct 2024