StretchBEV：在空间和时间上扩展未来实例预测
StretchBEV: Stretching Future Instance Prediction Spatially and Temporally
摘要：
在自动驾驶中，根据车辆周围所有智能体的位置和运动预测未来是规划的关键要求。最近，出现了一种新的联合制定的感知和预测，通过融合丰富的感官信息，从多个摄像机感知到一个紧凑的鸟瞰图表示执行预测。然而，未来预测的质量随着时间的推移而下降，同时由于多个合理的预测而延伸到更长的时间范围。在这项工作中，我们解决了这种固有的不确定性，在未来的预测与随机时间模型。我们的模型通过每个时间步的随机残差更新来学习潜在空间中的时间动态。通过在每个时间步从学习的分布中采样，我们获得了更多样化的未来预测，与以前的工作相比也更准确，特别是在场景中的空间上更远的区域和更长的时间范围内的时间上。尽管对每个时间步进行了单独处理，但我们的模型通过解耦动态学习和生成未来预测仍然有效。
英文摘要：
In self-driving, predicting future in terms of location and motion of all the agents around the vehicle is a crucial requirement for planning. Recently, a new joint formulation of perception and prediction has emerged by fusing rich sensory information perceived from multiple cameras into a compact bird's-eye view representation to perform prediction. However, the quality of future predictions degrades over time while extending to longer time horizons due to multiple plausible predictions. In this work, we address this inherent uncertainty in future predictions with a stochastic temporal model. Our model learns temporal dynamics in a latent space through stochastic residual updates at each time step. By sampling from a learned distribution at each time step, we obtain more diverse future predictions that are also more accurate compared to previous work, especially stretching both spatially further regions in the scene and temporally over longer time horizons. Despite separate processing of each time step, our model is still efficient through decoupling of the learning of dynamics and the generation of future predictions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
