README.md

---
license: gpl-3.0
pipeline_tag: depth-estimation
datasets:
- sayakpaul/nyu_depth_v2
---

# LapDepth-release
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/monocular-depth-estimation-using-laplacian/monocular-depth-estimation-on-kitti-eigen)](https://paperswithcode.com/sota/monocular-depth-estimation-on-kitti-eigen?p=monocular-depth-estimation-using-laplacian)
[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/monocular-depth-estimation-using-laplacian/monocular-depth-estimation-on-nyu-depth-v2)](https://paperswithcode.com/sota/monocular-depth-estimation-on-nyu-depth-v2?p=monocular-depth-estimation-using-laplacian)

This repository is a Pytorch implementation of the paper [**"Monocular Depth Estimation Using Laplacian Pyramid-Based Depth Residuals"**](https://ieeexplore.ieee.org/document/9316778)

![LapDepth](https://raw.githubusercontent.com/tjqansthd/LapDepth-release/master/example/FIG1.png)

Minsoo Song, Seokjae Lim, and [Wonjun Kim*](https://sites.google.com/view/dcvl)  
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

# Official Repository: [LapDepth-release](https://github.com/tjqansthd/LapDepth-release)

# License: [GPL-3.0 license](https://github.com/tjqansthd/LapDepth-release/blob/master/LICENSE)

# Usage
```python
from model import LDRN
model = LDRN(max_depth=10.0)
model.load_state_dict(torch.load("lap_depth_nyu.pkl"), strict=False)
model.eval()
```