新的FlexDepth模型提供鲁棒、实时的驾驶深度估计 · 追踪4个来源

报道来源 [4]

1. Hugging Face Daily Papers TIER_1 English(EN) · 2026-07-01 10:18

   迈向鲁棒驾驶感知：一种灵活的尺度驱动系列用于自监督单目深度估计

   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…

2. arXiv cs.CV TIER_1 English(EN) · Zhaowen Zhu, Li Zhang, Yujie Chen, Tian Zhang, Yingjie Wang, Mingxia Zhan · 2026-07-02 04:00

   迈向鲁棒性驾驶感知：一种灵活的尺度驱动系列用于自监督单目深度估计

   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…

3. arXiv cs.CV TIER_1 English(EN) · Mingxia Zhan · 2026-07-01 10:18

   迈向鲁棒性驾驶感知：一种灵活的尺度驱动系列用于自监督单目深度估计

   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…

4. arXiv cs.CV TIER_1 English(EN) · Liang Wang · 2026-06-30 11:07

   DrivingDepth：稀疏提示的像素级尺度校正用于驾驶深度估计

   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…