Exposure Completing for Temporally Consistent Neural High Dynamic Range Video Rendering

TL;DR

This paper introduces a novel method for HDR video rendering that completes missing exposure information by interpolating neighboring frames, resulting in more temporally consistent and higher quality HDR videos.

Contribution

The paper proposes a new exposure completing paradigm that reconstructs absent exposures in HDR video, improving temporal consistency and reducing artifacts compared to existing methods.

Findings

Achieves state-of-the-art performance on standard benchmarks.

Reduces flickering, noise, and ghosting artifacts in HDR videos.

Demonstrates the effectiveness of exposure completing in HDR rendering.

Abstract

High dynamic range (HDR) video rendering from low dynamic range (LDR) videos where frames are of alternate exposure encounters significant challenges, due to the exposure change and absence at each time stamp. The exposure change and absence make existing methods generate flickering HDR results. In this paper, we propose a novel paradigm to render HDR frames via completing the absent exposure information, hence the exposure information is complete and consistent. Our approach involves interpolating neighbor LDR frames in the time dimension to reconstruct LDR frames for the absent exposures. Combining the interpolated and given LDR frames, the complete set of exposure information is available at each time stamp. This benefits the fusing process for HDR results, reducing noise and ghosting artifacts therefore improving temporal consistency. Extensive experimental evaluations on standard benchmarks demonstrate that our method achieves state-of-the-art performance, highlighting the importance of absent exposure completing in HDR video rendering. The code is available at https://github.com/cuijiahao666/NECHDR.