研究人员开发了两种新方法来改进驾驶场景下的自监督单目深度估计。FlexDepth引入了一个灵活的模型族，具有尺度驱动的解码器和两阶段训练策略，可独立处理静态和动态元素，以最小的计算开销实现了最先进的性能。另一方面，DrivingDepth通过使用稀疏LiDAR数据作为提示来校准冻结的基础模型，专注于纠正深度估计中的几何-尺度冲突，在保持密集视觉几何的同时实现了卓越的度量精度和一致性。 AI
影响 这些进展可能带来更可靠、更高效的自动驾驶汽车感知系统，尤其是在具有挑战性的驾驶条件下。
排序理由 该集群包含两篇研究论文，详细介绍了自监督单目深度估计的新方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.00736v1 Announce Type: new Abstract: Self-Supervised Monocular Depth Estimation (MDE) has garnered attention in recent years due to its independence from ground truth. However, most existing models are limited to a single scale and exhibit considerable performance degr…
Self-Supervised Monocular Depth Estimation (MDE) has garnered attention in recent years due to its independence from ground truth. However, most existing models are limited to a single scale and exhibit considerable performance degradation in complex driving environments. Network…
Dense depth estimation for autonomous driving faces a geometry-scale conflict: depth foundation models deliver pixel-aligned dense visual geometry without reliable metric scale, while projected LiDAR provides metric anchors that are sparse, noisy, and misaligned with image struct…