Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction
This work addresses a specific bottleneck in HDR imaging for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles the problem of limited quality in single-image HDR reconstruction from LDR images by proposing a continuous exposure value representation (CEVR) that generates LDR images with arbitrary exposure values, resulting in significantly improved HDR reconstruction as shown in experiments.
Deep learning is commonly used to reconstruct HDR images from LDR images. LDR stack-based methods are used for single-image HDR reconstruction, generating an HDR image from a deep learning-generated LDR stack. However, current methods generate the stack with predetermined exposure values (EVs), which may limit the quality of HDR reconstruction. To address this, we propose the continuous exposure value representation (CEVR), which uses an implicit function to generate LDR images with arbitrary EVs, including those unseen during training. Our approach generates a continuous stack with more images containing diverse EVs, significantly improving HDR reconstruction. We use a cycle training strategy to supervise the model in generating continuous EV LDR images without corresponding ground truths. Our CEVR model outperforms existing methods, as demonstrated by experimental results.