I. Introduction & Related Work
Artificial intelligence (AI)-enabled video processing presents a challenging problem because the high resolution, high dynamic range, and high frame rates of image sensors generate large amounts of data that must be processed in real-time [14], [28]. In particular, the data transmission between the image sensor and the off-chip processing unit leads to significant latency, energy, and bandwidth bottlenecks. This problem is further exacerbated in an autonomous driving scenario, where there are a plethora of other sensors, such as radars and inertial measurement units (IMUs), that also need to transmit data for intelligence processing, including perception and localization [30].