发表机构
Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MVP提出一种在运动域进行推测的视觉流水线，通过预测运动矢量外推感知结果，并在后台周期性校正漂移，在目标检测上实现尾部延迟降低66.8%、能耗节省46%，精度损失很小。
AI 中文摘要
连续视觉（CV）系统支撑着自动驾驶和增强现实等实时应用，在这些应用中，延迟、吞吐量和能量在移动平台上受到严格限制。然而，现代CV SoC流水线仍然将图像捕获和处理串行化，导致端到端延迟较高。先前的工作通过预测未来帧并推测性地运行像素域后端推理来降低延迟，但错误的预测会迫使在真实帧上重新执行，增加了能量和复杂性。我们提出了MVP，一种完全在运动域中运行的运动预测推测视觉流水线。MVP不预测完整图像，而是预测未来的运动矢量，并利用这些矢量在下一帧到达之前从先前处理的帧中外推感知结果。图像信号处理器（ISP）中的轻量级硬件扩展重用现有的运动估计逻辑来预测运动，面积和能量开销极小。MVP引入了一种调度模型，将运动外推作为默认路径，而后端完整推理在后台周期性运行，用于在关键路径之外进行漂移校正。它还支持可选的前端缩放，允许系统在低运动或可预测运动下减少传感器采样以节省能量。我们在目标检测上评估了MVP，展示了尾部延迟最多降低66.8%，能量节省46%，而精度损失很小。
英文摘要
Continuous Vision (CV) systems underpin real-time applications such as autonomous driving and augmented reality, where latency, throughput, and energy are tightly constrained on mobile platforms. Modern CV SoC pipelines, however, still serialize image capture and processing, leading to high end-to-end latency. Prior work reduces this latency by predicting future frames and running pixel-domain backend inference speculatively, but incorrect predictions force re-execution on real frames, increasing energy and complexity. We present MVP, a motion-predictive speculative vision pipeline that operates entirely in the motion domain. Instead of forecasting full images, MVP predicts future motion vectors and uses them to extrapolate perception results from previously processed frames before the next frame arrives. A lightweight hardware extension in the Image Signal Processor (ISP) reuses existing motion-estimation logic to predict motion with minimal area and energy cost. MVP introduces a scheduling model that treats motion extrapolation as the default path, while full backend inference runs periodically in the background for drift correction off the critical path. It also supports optional frontend scaling, allowing the system to reduce sensor sampling under low or predictable motion to save energy. We evaluate MVP on object detection, demonstrating up to 66.8% reduction in tail latency and 46% energy savings, at a small accuracy cost.
CommentsAccepted to the 59th IEEE/ACM International Symposium on Microarchitecture (MICRO 2026)
