一句话：提出节奏像素区域多分辨率视觉传感系统，按区域动态降分辨率，以低内存能耗实现高精度视觉计算。
高时空分辨率视觉帧能提升视觉应用（如增强现实）的精度，但捕获与处理高分辨率帧会带来昂贵的内存流量与能耗；低分辨率帧虽可降低像素内存吞吐，却会牺牲高精度视觉感知机会。论文的核心直觉是并非场景所有部分都需要统一分辨率。为此，作者提出 Rhythmic Pixel Regions 多分辨率视觉传感系统，选择性地、机会性地对不同图像区域降低分辨率，从而在能效较高的内存数据率下支持高精度视觉计算。摘要侧重系统动机与设计思想，未给出具体实现细节和定量评估结果。
High spatiotemporal resolution can offer high precision for vision applications, which is particularly useful to capture the nuances of visual features, such as for augmented reality. Unfortunately, capturing and processing high spatiotemporal visual frames generates energy-expensive memory traffic. On the other hand, low resolution frames can reduce pixel memory throughput, but reduce also the opportunities of high-precision visual sensing. However, our intuition is that not all parts of the scene need to be captured at a uniform resolution. Selectively and opportunistically reducing resolution for different regions of image frames can yield high-precision visual computing at energy-efficient memory data rates.
DOI 原文 ·
@inproceedings{paperbot6106,
title = {Rhythmic pixel regions: multi-resolution visual sensing system towards high-precision visual computing at low power},
author = {Venkatesh Kodukula and Alexander Shearer and Van Nguyen and Srinivas Lingutla and Yifei Liu and Robert LiKamWa},
booktitle = {ASPLOS},
year = {2021},
doi = {10.1145/3445814.3446737}
}