Self-Gated Memory Recurrent Network for Efficient Scalable HDR Deghosting
This work addresses ghosting in HDR imaging for computer vision applications, presenting an incremental improvement with a novel recurrent cell architecture.
The authors tackled the problem of ghosting artifacts in high dynamic range (HDR) imaging from dynamic sequences by proposing a recurrent network method that achieves state-of-the-art performance on three public datasets while being scalable to variable-length inputs without retraining.
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.