| dc.contributor | 資訊系 | |
| dc.creator (作者) | 彭彥璁 | |
| dc.creator (作者) | Peng, Yan-Tsung;Yu, Shih-Hsien;Lin, Yi-Ting;Yu, Chih-Hsuan | |
| dc.date (日期) | 2025-07 | |
| dc.date.accessioned | 20-Jan-2026 13:18:58 (UTC+8) | - |
| dc.date.available | 20-Jan-2026 13:18:58 (UTC+8) | - |
| dc.date.issued (上傳時間) | 20-Jan-2026 13:18:58 (UTC+8) | - |
| dc.identifier.uri (URI) | https://ah.lib.nccu.edu.tw/item?item_id=180740 | - |
| dc.description.abstract (摘要) | Variations in color temperature across different lighting conditions can introduce color distortions in images, making them appear different from human visual perception. Addressing these color shifts to achieve white balance (WB) remains a complex problem, as it requires detecting and compensating for color tone deviations caused by diverse illumination sources. Recent advances in deep learning have revolutionized WB techniques, moving beyond conventional illumination estimation to directly transforming color-shifted images into accurately color-balanced outputs. In this paper, we propose a new WB algorithm using color-histogram prediction for consistent and accurate color rendering. Comprehensive experiments conducted on public benchmark datasets validate the superiority of our method, demonstrating enhanced color fidelity and robustness compared to existing state-of-the-art techniques. | |
| dc.format.extent | 118 bytes | - |
| dc.format.mimetype | text/html | - |
| dc.relation (關聯) | 2025 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-Taiwan), Institute of Electrical and Electronics Engineers (IEEE) | |
| dc.subject (關鍵詞) | White balance; color correction; histogram specification; transformer networks | |
| dc.title (題名) | White Balance Using Histogram Prediction Prior | |
| dc.type (資料類型) | conference | |
| dc.identifier.doi (DOI) | 10.1109/ICCE-Taiwan66881.2025.11207977 | |
| dc.doi.uri (DOI) | https://doi.org/10.1109/ICCE-Taiwan66881.2025.11207977 | |
