用虚拟数据训练轻量级模型，实现高效精准的单目深度估计。
Depth as Points: Center Point-based Depth Estimation
- 基于关键点构建虚拟数据，快速生成专用数据集
- 在复杂高度分布下仍保持高精度与低延迟
- 适合资源受限的自动驾驶实时场景
城市环境中对车辆和行人的感知对自动驾驶至关重要，但传统方法依赖复杂的数据采集，计算和硬件成本高。为此，我们首先提出一种高效的虚拟数据生成方法，可在短时间内构建任务与场景定制的数据集。基于该方法，我们构建了大规模多任务自动驾驶数据集VirDepth。随后，我们提出CenterDepth，一种用于单目深度估计的轻量级架构，具备高运行效率，在高度分布极不均衡的情况下仍表现优异。该模型通过创新的Center FC-CRFs算法融合全局语义信息，基于目标关键点聚合多尺度特征，实现基于检测的深度估计。实验表明，所提方法在计算速度和预测精度上均优于现有方案。
原文摘要 · Abstract (English)
The perception of vehicles and pedestrians in urban scenarios is crucial for autonomous driving. This process typically involves complicated data collection, imposes high computational and hardware demands. To address these limitations, we first develop a highly efficient method for generating virtual datasets, which enables the creation of task- and scenario-specific datasets in a short time. Leveraging this method, we construct the virtual depth estimation dataset VirDepth, a large-scale, multi-task autonomous driving dataset. Subsequently, we propose CenterDepth, a lightweight architecture for monocular depth estimation that ensures high operational efficiency and exhibits superior performance in depth estimation tasks with highly imbalanced height-scale distributions. CenterDepth integrates global semantic information through the innovative Center FC-CRFs algorithm, aggregates multi-scale features based on object key points, and enables detection-based depth estimation of targets. Experiments demonstrate that our proposed method achieves superior performance in terms of both computational speed and prediction accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。