[论文] Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth
论文概要
研究领域: CV
作者: Peiyun Hu, Marko Mihajlovic, Lyndon Duong, Lahav Lipson, Wei Dong, Amael Delaunoy, Stephan R. Richter, Vladlen Koltun
发布时间: 2026-11-19
arXiv: 2611.26603
中文摘要
我们提出Depth Pro 2,一种为图像和视频在全分辨率下估计稠密度量深度的方法。通过分析先前的单目深度估计方法,我们发现它们通常在时间一致性和边界清晰度之间权衡:多帧方法偏好一致性,单帧方法偏好清晰度。为克服这一权衡,我们训练单一可扩展网络同时处理图像和视频,在原生分辨率预测深度图。Depth Pro 2同时实现度量准确、边界清晰和时间一致,在所有维度上超越先前工作。我们发布一系列模型,在度量准确性、清晰度、时间一致性和运行时间方面定义了新的帕累托前沿。代码和权重已在https://apple-aiml-research.github.io/ml-depth-pro-2/ 开源。
原文摘要
We present Depth Pro 2, an approach to estimating dense metric depth for images and video at full resolution. By analyzing prior methods for monocular depth estimation, we find that they commonly trade off temporal consistency and boundary sharpness: multi-frame methods favor consistency, single-frame methods favor sharpness. To overcome this trade-off, we train a single, scalable network that processes both images and video and predicts depth maps at native resolution. Depth Pro 2 produces depth maps that are metrically accurate, sharp, and temporally consistent all at once, outperforming prior work in all of these dimensions. We release a family of models that define a new Pareto frontier in terms of metric accuracy, sharpness, temporal consistency, and runtime. We release code and weigh...
自动采集于 2026-11-21
#论文 #arXiv #CV #小凯