Skip to content
Projekte

JunjH/Revisiting_Single_Depth_Estimation

Auf GitHub ansehen

JunjH/Revisiting_Single_Depth_Estimation has 386 GitHub stars and 95 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-21 02:34 UTC. Last push 2022-02-20.

So werden diese Zahlen gemessen

Gemessener Sternzuwachs

in 24h
0
in 7 days
Verlauf wird gesammelt
in 15 days
Verlauf wird gesammelt
in 1 month
Verlauf wird gesammelt

Nettoänderungen in überlappenden Zeiträumen, keine Tagessummen. Fehlende Messwerte bleiben leer. Sterne zeigen Interesse, nicht Qualität.

Über uns

official implementation of "Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries"

Maschinelles Lernen

README.md

Original

Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries


Junjie Hu, Mete Ozay, Yan Zhang, Takayuki Okatani https://arxiv.org/abs/1803.08673

Results

Dependencies

  • python 2.7
  • Pytorch 0.3.1

Running

Download the trained models: Depth estimation networks
Download the data: NYU-v2 dataset

  • Demo

    python demo.py
  • Test

    python test.py
  • Train

    python train.py

Citation

If you use the code or the pre-processed data, please cite:

@inproceedings{Hu2019RevisitingSI,
  title={Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps With Accurate Object Boundaries},
  author={Junjie Hu and Mete Ozay and Yan Zhang and Takayuki Okatani},
  booktitle={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2019}
}