# \#omnidir

**URL:** https://forum.opencv.org/tag/omnidir/375.md

[Latest](https://forum.opencv.org/latest.md) · [Categories](https://forum.opencv.org/categories.md) · [Tags](https://forum.opencv.org/tags.md)

---

## [There seems something wrong about depth calculation in cv::omnidir::stereoReconstruct function](https://forum.opencv.org/t/there-seems-something-wrong-about-depth-calculation-in-cv-stereoreconstruct-function/13328)

<div class="topic-metadata">

**Author:** [@yuan\_wentao](https://forum.opencv.org/u/yuan_wentao)\
**Replies:** 0\
**Last updated:** [May 27, 2023, 6:00pm UTC](https://forum.opencv.org/t/there-seems-something-wrong-about-depth-calculation-in-cv-stereoreconstruct-function/13328 "2023-05-27T18:00:10Z")

</div>

I am confused about the implementation of absolute depth calculation in omnidir.cpp, which is different from the original paper (Binocular Spherical Stereo). specifically, the depth is calculated as follows: float dept…