Deep Progressive Feature Aggregation Network for High Dynamic Range Imaging

TL;DR

This paper introduces a deep progressive feature aggregation network that enhances HDR imaging in dynamic scenes by reducing ghosting artifacts and restoring details using multi-frequency feature decomposition.

Contribution

It proposes a novel deep network with coarse-to-fine feature aggregation and wavelet-based decomposition to improve HDR quality in scenes with motion.

Findings

Achieves state-of-the-art HDR quality in dynamic scenes.

Produces images with fewer distortions and more detail.

Outperforms existing HDR methods in experiments.

Abstract

High dynamic range (HDR) imaging is an important task in image processing that aims to generate well-exposed images in scenes with varying illumination. Although existing multi-exposure fusion methods have achieved impressive results, generating high-quality HDR images in dynamic scenes is still difficult. The primary challenges are ghosting artifacts caused by object motion between low dynamic range images and distorted content in under and overexposed regions. In this paper, we propose a deep progressive feature aggregation network for improving HDR imaging quality in dynamic scenes. To address the issues of object motion, our method implicitly samples high-correspondence features and aggregates them in a coarse-to-fine manner for alignment. In addition, our method adopts a densely connected network structure based on the discrete wavelet transform, which aims to decompose the input features into multiple frequency subbands and adaptively restore corrupted contents. Experiments show that our proposed method can achieve state-of-the-art performance under different scenes, compared to other promising HDR imaging methods. Specifically, the HDR images generated by our method contain cleaner and more detailed content, with fewer distortions, leading to better visual quality.