---
title: dpt-swin2-tiny-256
canonical_url: "https://www.modelscope.cn/models/cubeai/dpt-swin2-tiny-256"
md_url: "https://www.modelscope.cn/models/cubeai/dpt-swin2-tiny-256.md"
repository: cubeai/dpt-swin2-tiny-256
chinese_name: "单目深度估计(dpt-swin2-tiny-256)"
last_updated: 2024-08-27
license: "Apache License 2.0"
pipeline_tag: image-depth-estimation
tasks:
  - image-depth-estimation
library_name:
  - pytorch
frameworks:
  - Pytorch
downloads: 51
stars: 0
---

# dpt-swin2-tiny-256

> dpt-swin2-tiny-256 - cubeai 在 ModelScope 开源的模型。单目深度估计(dpt-swin2-tiny-256)

cubeai/dpt-swin2-tiny-256 是 ModelScope 魔搭社区上的image-depth-estimation模型，采用 Apache License 2.0 许可。

- **Repository**: cubeai/dpt-swin2-tiny-256
- **License**: Apache License 2.0
- **Tasks**: image-depth-estimation
- **Downloads**: 51
- **Stars**: 0
- **Last updated**: 2024-08-27

Source: https://www.modelscope.cn/models/cubeai/dpt-swin2-tiny-256

---

# 单目深度估计(dpt-swin2-tiny-256)

Robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022" 

## 模型来源

https://github.com/isl-org/MiDaS

## 使用

https://openi.pcl.ac.cn/cubeai-model-zoo/dpt-swin2-tiny-256