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

arXiv:2403.10376v1 Announce Type: new
Abstract: 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 …

abstract art arxiv attention balance challenges cs.cv demand gpus however images imaging inference nature practical self-attention state temporal transformer transformer attention type via