English

Self-Gated Memory Recurrent Network for Efficient Scalable HDR Deghosting

Computer Vision and Pattern Recognition 2021-12-28 v1

Abstract

We propose a novel recurrent network-based HDR deghosting method for fusing arbitrary length dynamic sequences. The proposed method uses convolutional and recurrent architectures to generate visually pleasing, ghosting-free HDR images. We introduce a new recurrent cell architecture, namely Self-Gated Memory (SGM) cell, that outperforms the standard LSTM cell while containing fewer parameters and having faster running times. In the SGM cell, the information flow through a gate is controlled by multiplying the gate's output by a function of itself. Additionally, we use two SGM cells in a bidirectional setting to improve output quality. The proposed approach achieves state-of-the-art performance compared to existing HDR deghosting methods quantitatively across three publicly available datasets while simultaneously achieving scalability to fuse variable-length input sequence without necessitating re-training. Through extensive ablations, we demonstrate the importance of individual components in our proposed approach. The code is available at https://val.cds.iisc.ac.in/HDR/HDRRNN/index.html.

Keywords

Cite

@article{arxiv.2112.13050,
  title  = {Self-Gated Memory Recurrent Network for Efficient Scalable HDR Deghosting},
  author = {K. Ram Prabhakar and Susmit Agrawal and R. Venkatesh Babu},
  journal= {arXiv preprint arXiv:2112.13050},
  year   = {2021}
}

Comments

12 pages

R2 v1 2026-06-24T08:30:58.092Z