Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.16685 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914770534268928 |
|---|---|
| author | Zhai, Huiyu Chen, Mo Yang, Xingxing Kang, Gusheng |
| author_facet | Zhai, Huiyu Chen, Mo Yang, Xingxing Kang, Gusheng |
| contents | The NIR-to-RGB spectral domain translation is a formidable task due to the inherent spectral mapping ambiguities within NIR inputs and RGB outputs. Thus, existing methods fail to reconcile the tension between maintaining texture detail fidelity and achieving diverse color variations. In this paper, we propose a Multi-scale HSV Color Feature Embedding Network (MCFNet) that decomposes the mapping process into three sub-tasks, including NIR texture maintenance, coarse geometry reconstruction, and RGB color prediction. Thus, we propose three key modules for each corresponding sub-task: the Texture Preserving Block (TPB), the HSV Color Feature Embedding Module (HSV-CFEM), and the Geometry Reconstruction Module (GRM). These modules contribute to our MCFNet methodically tackling spectral translation through a series of escalating resolutions, progressively enriching images with color and texture fidelity in a scale-coherent fashion. The proposed MCFNet demonstrates substantial performance gains over the NIR image colorization task. Code is released at: https://github.com/AlexYangxx/MCFNet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_16685 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-scale HSV Color Feature Embedding for High-fidelity NIR-to-RGB Spectrum Translation Zhai, Huiyu Chen, Mo Yang, Xingxing Kang, Gusheng Computer Vision and Pattern Recognition Artificial Intelligence The NIR-to-RGB spectral domain translation is a formidable task due to the inherent spectral mapping ambiguities within NIR inputs and RGB outputs. Thus, existing methods fail to reconcile the tension between maintaining texture detail fidelity and achieving diverse color variations. In this paper, we propose a Multi-scale HSV Color Feature Embedding Network (MCFNet) that decomposes the mapping process into three sub-tasks, including NIR texture maintenance, coarse geometry reconstruction, and RGB color prediction. Thus, we propose three key modules for each corresponding sub-task: the Texture Preserving Block (TPB), the HSV Color Feature Embedding Module (HSV-CFEM), and the Geometry Reconstruction Module (GRM). These modules contribute to our MCFNet methodically tackling spectral translation through a series of escalating resolutions, progressively enriching images with color and texture fidelity in a scale-coherent fashion. The proposed MCFNet demonstrates substantial performance gains over the NIR image colorization task. Code is released at: https://github.com/AlexYangxx/MCFNet. |
| title | Multi-scale HSV Color Feature Embedding for High-fidelity NIR-to-RGB Spectrum Translation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2404.16685 |