Leveraging Transformer attention has led to great advancements in HDR
deghosting. However, the intricate nature of self-attention introduces
practical challenges, as existing state-of-the-art methods often demand
high-end GPUs or exhibit slow inference speeds, especially for high-resolution
images like 2K. Striking an optimal balance between performance and latency
remains a critical concern. In response, this work presents PASTA, a novel
Progressively Aggregated Spatio-Temporal Alignment framework for HDR
deghosting. Our approach achieves effectiveness and efficiency by harnessing
hierarchical representation during feature distanglement. Through the
utilization of diverse granularities within the hierarchical structure, our
method substantially boosts computational speed and optimizes the HDR imaging
workflow. In addition, we explore within-scale feature modeling with local and
global attention, gradually merging and refining them in a coarse-to-fine
fashion. Experimental results showcase PASTA's superiority over current SOTA
methods in both visual quality and performance metrics, accompanied by a
substantial 3-fold (x3) increase in inference speed.

PASTA 是一种新颖的渐进聚合空时对齐框架，通过利用层次表示进行特征分解，从而实现高效性和效果性。通过在层次结构中利用不同的粒度，我们的方法极大地提升了计算速度并优化了 HDR 成像工作流程。实验结果展示了 PASTA 在视觉质量和性能指标上相对于当前最先进方法的优势，推理速度大幅增加了 3 倍（x3）。

PASTA：通过逐步聚合时空对齐实现灵活高效的 HDR 图像处理

PASTA: Towards Flexible and Efficient HDR Imaging Via Progressively  Aggregated Spatio-Temporal Aligment

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 this https URL

本文提出了一种基于递归网络的 HDR 去霓虹方法，使用卷积和递归的结构以生成视觉效果良好，没有去霓虹的 HDR 图像。该方法引入了一种新的递归单元结构，即自门内存（SGM）单元，它优于标准 LSTM 单元，同时包含更少的参数并具有更快的运行时间。 在双向设置中使用两个 SGM 单元可提高输出质量，并在不需要重新训练的情况下同时实现了对变长输入序列的可扩展性。此方法在三个公开可用数据集上在数量上比现有的 HDR 去霓虹方法具有最先进的性能。通过全面的消融实验，我们证明了所提出方法中各个组成部分的重要性。