FHDR: HDR Image Reconstruction from a Single LDR Image using Feedback Network

TL;DR

This paper introduces FHDR, a feedback neural network that iteratively reconstructs high dynamic range images from a single low dynamic range image, achieving improved quality with fewer parameters.

Contribution

The paper proposes a novel feedback-based neural network architecture for HDR reconstruction, utilizing multiple iterations for coarse-to-fine image enhancement.

Findings

Outperforms state-of-the-art HDR reconstruction methods

Achieves better quality with fewer network parameters

Enables early and iterative reconstruction process

Abstract

High dynamic range (HDR) image generation from a single exposure low dynamic range (LDR) image has been made possible due to the recent advances in Deep Learning. Various feed-forward Convolutional Neural Networks (CNNs) have been proposed for learning LDR to HDR representations. To better utilize the power of CNNs, we exploit the idea of feedback, where the initial low level features are guided by the high level features using a hidden state of a Recurrent Neural Network. Unlike a single forward pass in a conventional feed-forward network, the reconstruction from LDR to HDR in a feedback network is learned over multiple iterations. This enables us to create a coarse-to-fine representation, leading to an improved reconstruction at every iteration. Various advantages over standard feed-forward networks include early reconstruction ability and better reconstruction quality with fewer network parameters. We design a dense feedback block and propose an end-to-end feedback network- FHDR for HDR image generation from a single exposure LDR image. Qualitative and quantitative evaluations show the superiority of our approach over the state-of-the-art methods.