MapPrior：基于生成模型的鸟瞰图地图布局估计
MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models
AI总结：
针对现有鸟瞰图感知模型生成地图布局真实性不足、无法应对传感器信息不确定性的问题，提出结合判别式模型与生成模型的MapPrior框架，在nuScenes基准上的表现优于现有最优方法，相关评估得分显著提升。
摘要：
尽管鸟瞰图（BEV）感知领域已取得巨大进展，但现有模型在生成真实且连贯的语义地图布局方面仍存在不足，且无法应对由部分传感器信息（如遮挡或覆盖范围有限）带来的不确定性。本研究提出MapPrior，这是一种新型BEV感知框架，将传统的判别式BEV感知模型与经训练的语义地图布局生成模型相结合。我们的MapPrior能输出准确率更高、真实感更强且具备不确定性感知能力的预测结果。我们在大规模nuScenes基准上对模型进行了评估。在提交时，MapPrior的性能优于最强的对比方法，在基于相机和LiDAR的BEV感知任务中，MMD和ECE得分均得到显著提升。
英文摘要：
Despite tremendous advancements in bird's-eye view (BEV) perception, existing models fall short in generating realistic and coherent semantic map layouts, and they fail to account for uncertainties arising from partial sensor information (such as occlusion or limited coverage). In this work, we introduce MapPrior, a novel BEV perception framework that combines a traditional discriminative BEV perception model with a learned generative model for semantic map layouts. Our MapPrior delivers predictions with better accuracy, realism, and uncertainty awareness. We evaluate our model on the large-scale nuScenes benchmark. At the time of submission, MapPrior outperforms the strongest competing method, with significantly improved MMD and ECE scores in camera- and LiDAR-based BEV perception.
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。
