End-to-end ultra-high-resolution portrait enhancement based on ISP curve prediction
Portrait images often suffer from poor colour, low contrast, and improper exposure. Ultra-high-resolution enhancement relies on manual adjustments, while deep-learning methods are limited by large parameter requirements and insufficient high-quality training samples. This study proposes an end-to-end ultra-high-resolution portrait enhancement method using image signal processing (ISP) curve prediction, with a global ISP branch and a local curve branch. The global branch uses cross-attention for global modelling and predict a colour correction matrix and gamma parameters. The local branch extracts low-resolution features using a lightweight convolutional residual structure and predicts spatially varying residual mappings parameterized by RGB values and spatial coordinates for full-resolution enhancement. Extensive comparative experiments were conducted on the ALSPP5 K multi-scene portrait, MIT-Adobe FiveK, and HDR + datasets. On MIT-Adobe FiveK, the proposed method achieves 25.67 dB PSNR, 0.960 SSIM, and 0.032 LPIPS. Compared with Star-Enhancer, this corresponds to a 0.23 dB increase in PSNR, a 0.012 increase in SSIM, and a reduction in LPIPS from 0.083 to 0.032 (approximately 61.4%).
Authors
- Yuanlin Zheng (ORCID: https://orcid.org/0000-0002-8490-4458)
- Kaiyang Liao (ORCID: https://orcid.org/0000-0003-0833-2336)
- Congjun Zhong
- Bangyong Sun
- Jie He
- Hongbo Huo
- Bing Chen
Institutions
- Xi'an University of Technology (CN)
Publication Details
- Journal
- The Imaging Science Journal
- Published
- 2026-11-18
- DOI
- https://doi.org/10.1080/13682199.2026.2761382
- Primary Topic
- Image Enhancement Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China