HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset

TL;DR

This paper introduces a novel coarse-to-fine deep learning framework for HDR video reconstruction from alternating exposure sequences, along with a new benchmark dataset for evaluation, achieving superior results over existing methods.

Contribution

The paper proposes a new deep learning approach combining coarse and fine alignment in image and feature spaces, and provides the first comprehensive HDR video dataset for benchmarking.

Findings

Outperforms previous state-of-the-art methods in HDR video reconstruction

Introduces a new benchmark dataset with 97 static and 184 dynamic scene sequences

Demonstrates the effectiveness of coarse-to-fine alignment in improving HDR quality

Abstract

High dynamic range (HDR) video reconstruction from sequences captured with alternating exposures is a very challenging problem. Existing methods often align low dynamic range (LDR) input sequence in the image space using optical flow, and then merge the aligned images to produce HDR output. However, accurate alignment and fusion in the image space are difficult due to the missing details in the over-exposed regions and noise in the under-exposed regions, resulting in unpleasing ghosting artifacts. To enable more accurate alignment and HDR fusion, we introduce a coarse-to-fine deep learning framework for HDR video reconstruction. Firstly, we perform coarse alignment and pixel blending in the image space to estimate the coarse HDR video. Secondly, we conduct more sophisticated alignment and temporal fusion in the feature space of the coarse HDR video to produce better reconstruction. Considering the fact that there is no publicly available dataset for quantitative and comprehensive evaluation of HDR video reconstruction methods, we collect such a benchmark dataset, which contains $97$ sequences of static scenes and 184 testing pairs of dynamic scenes. Extensive experiments show that our method outperforms previous state-of-the-art methods. Our dataset, code and model will be made publicly available.