Deep Learning for HDR Imaging: State-of-the-Art and Future Trends
arXiv:2110.10394
Abstract
High dynamic range (HDR) imaging is a technique that allows an extensive dynamic range of exposures, which is important in image processing, computer graphics, and computer vision. In recent years, there has been a significant advancement in HDR imaging using deep learning (DL). This study conducts a comprehensive and insightful survey and analysis of recent developments in deep HDR imaging methodologies. We hierarchically and structurally group existing deep HDR imaging methods into five categories based on (1) number/domain of input exposures, (2) number of learning tasks, (3) novel sensor data, (4) novel learning strategies, and (5) applications. Importantly, we provide a constructive discussion on each category regarding its potential and challenges. Moreover, we review some crucial aspects of deep HDR imaging, such as datasets and evaluation metrics. Finally, we highlight some open problems and point out future research directions.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), main and suppl. material
References in corpus (10)
- Conditional Generative Adversarial Nets
- Deep Bilateral Learning for Real-Time Image Enhancement
- HDR image reconstruction from a single exposure using deep CNNs
- Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time
- HDR Video Reconstruction with Tri-Exposure Quad-Bayer Sensors
- All-Weather Deep Outdoor Lighting Estimation
- ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging
- HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization
- Deep Inverse Tone Mapping Using LDR Based Learning for Estimating HDR Images with Absolute Luminance
- SiamEvent: Event-based Object Tracking via Edge-aware Similarity Learning with Siamese Networks