Deep Snapshot HDR Imaging Using Multi-Exposure Color Filter Array
This work addresses the problem of high-quality HDR image reconstruction for photographers and computer vision applications, offering an incremental improvement over existing snapshot methods.
This paper proposes a deep snapshot high dynamic range (HDR) imaging framework that reconstructs an HDR image from RAW data captured by a multi-exposure color filter array (ME-CFA). The framework introduces luminance normalization, which improves visual image quality in tone-mapped domains by equally handling errors in bright and dark areas. It outperforms other snapshot methods on two public HDR datasets.
In this paper, we propose a deep snapshot high dynamic range (HDR) imaging framework that can effectively reconstruct an HDR image from the RAW data captured using a multi-exposure color filter array (ME-CFA), which consists of a mosaic pattern of RGB filters with different exposure levels. To effectively learn the HDR image reconstruction network, we introduce the idea of luminance normalization that simultaneously enables effective loss computation and input data normalization by considering relative local contrasts in the "normalized-by-luminance" HDR domain. This idea makes it possible to equally handle the errors in both bright and dark areas regardless of absolute luminance levels, which significantly improves the visual image quality in a tone-mapped domain. Experimental results using two public HDR image datasets demonstrate that our framework outperforms other snapshot methods and produces high-quality HDR images with fewer visual artifacts.