HDRVideo-GAN: Deep Generative HDR Video Reconstruction
This addresses the challenge of capturing high-quality HDR video with conventional cameras for applications in video production and viewing, though it is incremental as it builds on existing optical flow and GAN methods.
The paper tackles the problem of reconstructing high dynamic range (HDR) videos from low dynamic range (LDR) sequences with alternating exposures, proposing an end-to-end GAN-based framework that achieves state-of-the-art performance and generates superior quality HDR frames.
High dynamic range (HDR) videos provide a more visually realistic experience than the standard low dynamic range (LDR) videos. Despite having significant progress in HDR imaging, it is still a challenging task to capture high-quality HDR video with a conventional off-the-shelf camera. Existing approaches rely entirely on using dense optical flow between the neighboring LDR sequences to reconstruct an HDR frame. However, they lead to inconsistencies in color and exposure over time when applied to alternating exposures with noisy frames. In this paper, we propose an end-to-end GAN-based framework for HDR video reconstruction from LDR sequences with alternating exposures. We first extract clean LDR frames from noisy LDR video with alternating exposures with a denoising network trained in a self-supervised setting. Using optical flow, we then align the neighboring alternating-exposure frames to a reference frame and then reconstruct high-quality HDR frames in a complete adversarial setting. To further improve the robustness and quality of generated frames, we incorporate temporal stability-based regularization term along with content and style-based losses in the cost function during the training procedure. Experimental results demonstrate that our framework achieves state-of-the-art performance and generates superior quality HDR frames of a video over the existing methods.