Vectorized high-definition (HD) maps are essential for an autonomous driving system. Recently, state-of-the-art map vectorization methods are mainly based on DETR-like framework to generate HD maps in an end-to-end manner. In this paper, we propose InteractionMap, which improves previous map vectorization methods by fully leveraging local-to-global information interaction in both time and space. Firstly, we explore enhancing DETR-like detectors by explicit position relation prior from point-level to instance-level, since map elements contain strong shape priors. Secondly, we propose a key-frame-based hierarchical temporal fusion module, which interacts temporal information from local to global. Lastly, the separate classification branch and regression branch lead to the problem of misalignment in the output distribution. We interact semantic information with geometric information by introducing a novel geometric-aware classification loss in optimization and a geometric-aware matching cost in label assignment. InteractionMap achieves state-of-the-art performance on both nuScenes and Argoverse2 benchmarks.

In this paper, we proposed a new rate control algorithm for High Efficiency Video Coding (HEVC), the latest video coding standard from the ITU/ISO. We use the information of pre-encoded 16x16 coding units (CUs) to estimate the characteristics of the largest coding unit (LCU). Based on the estimates, the proposed R -- λ model can be refined before the real encoding process. This is in contrast to rate control algorithms such as that in the HEVC reference software, where the model is updated based on a previously encoded picture. Experimental results show that the proposed rate control scheme can achieve accurate rate control with a BD-PSNR gain up to 5.37dB, compared to the state-of-the-art rate control algorithm in the HEVC test model (HM) 16.0. The largest PSNR improvement was over 6dB.