Depth Anything

AI绘画模型—

Depth Anything

网站核心内容概述
该网站主要展示了与深度学习及计算机视觉相关的多个资源和内容，包括研究论文、代码、演示以及模型应用。网站的核心内容涉及到多个技术领域的最新研究成果与工具，旨在为相关领域的研究者和开发者提供实用资源。

主要功能与内容：

1. 研究人员

   • Hengshuang Zhao

   • Bingyi Kang

   • Model：模型及其应用

   • Code：相关代码资源

   • Paper：具体研究论文

   • Zilong Huang

   • 相关技术

     • MagicEdit：与深度编辑相关的技术应用

     • Xiaogang Xu

     • Nerfies：技术相关项目或工具

     • 资源

       • arXiv：论文链接与研究资料

       • Demo：演示内容

       • Jiashi Feng

       • 研究人员

         • Lihe Yang

       • 资源

         • arXiv：论文链接与研究资料

         • Paper：具体研究论文

         • Code：相关代码资源

         • Demo：演示内容

         • Model：模型及其应用

       • 相关技术

         • MagicEdit：与深度编辑相关的技术应用

         • Nerfies：技术相关项目或工具

网站内容整理：

盾灵安全导航

This work presents Depth Anything, a highly practical solution for robust monocular depth estimation. Without pursuing novel technical modules, we aim to build a simple yet powerful foundation model dealing with any images under any circumstances. To this end, we scale up the dataset by designing a data engine to collect and automatically annotate large-scale unlabeled data (~62M), which significantly enlarges the data coverage and thus is able to reduce the generalization error. We investigate two simple yet effective strategies that make data scaling-up promising. First, a more challenging optimization target is created by leveraging data augmentation tools. It compels the model to actively seek extra visual knowledge and acquire robust representations. Second, an auxiliary supervision is developed to enforce the model to inherit rich semantic priors from pre-trained encoders. We evaluate its zero-shot capabilities extensively, including six public datasets and randomly captured photos. It demonstrates impressive generalization ability. Further, through fine-tuning it with metric depth information from NYUv2 and KITTI, new SOTAs are set. Our better depth model also results in a much better depth-conditioned ControlNet. All models have been released.

We thank the MagicEdit team for providing some video examples for video depth estimation, and Tiancheng Shen for evaluating the depth maps with MagicEdit. The middle video is generated by MiDaS-based ControlNet, while the last video is generated by Depth Anything-based ControlNet.