[ECCV 2026] Track4World:面向世界中心的全像素前馈稠密 3D 跟踪
depthanything 开源项目推荐(6 个)
depthanything 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 全部 6
GitHub 共 6 个仓库,已全部展示This repository demonstrates browser based implementation of DepthAnything and DepthAnythingV2 models. It is powered by Onnx and does not require any web servers or APIs.
DepthAnything算法的c++实现,包括TensorRT、RKNN、OnnxRuntime三种硬件平台(推理引擎).
A Lightweight Deep Learning Model for Depth Estimation. Aimed to run on edge devices and provide near-real-time results. This project uses knowledge distillation technology to transfer knowledge from DepthAnythingV2 to a smaller model
Real-time depth anything model 2 with GPU acceleration supports Apple silicon GPU's .
Robot Vision Demo provides depth-based navigation for robots using DepthAnything, processing camera feeds to generate structured navigation commands. The system analyzes depth data across image regions, detects objects, and visualizes results through a responsive web interface for real-time monitoring and control.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 6 个项目;原始页面见 https://github.com/topics/depthanything。
- 该话题在 GitHub 上共有 6 个仓库, 本站收录的是其中最热门的 6 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 6 个项目累计 435 Star,覆盖 4 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。