跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.26603 · v1

Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth

Depth Pro 2:锐利且时序一致的度量单目深度

首次提交 2026-11-20 02:55
版本更新 2026-11-20 02:55
雷达观测 2026-11-20 12:52
arXiv ↗PDF ↗

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 weights at https://apple-aiml-research.github.io/ml-depth-pro-2/

作者备注:Code and weights available at https://apple-aiml-research.github.io/ml-depth-pro-2/

AI 论文解读

基于摘要 · 非全文审阅

Depth Pro 2 用一个可扩展的单一网络同时处理图像与视频,在原生分辨率下预测兼具度量准确、边界锐利与时序一致的稠密深度。

正在读取账号与研究记录…

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-20 02:55 · 最新观测版本

Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth

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 weights at https://apple-aiml-research.github.io/ml-depth-pro-2/

查看此版本解读 →查看此版本原文 ↗