isl-org / isl-org/Open3D

How to run Color Map Optimization pipeline successfully with our custom mesh?

Open
#6,017 1 comment 0 reactions 0 assignees View on GitHub
question
Dominant language
C++
Stars
14k
Forks
2.6k
Avg merge
5d 18h
Merged PRs (30d)
6

Description

### Checklist

- [X] I have searched for [similar issues](https://github.com/isl-org/Open3D/issues).
- [X] For Python issues, I have tested with the [latest development wheel](http://www.open3d.org/docs/latest/getting_started.html#development-version-pip).
- [X] I have checked the [release documentation](http://www.open3d.org/docs/release/) and the [latest documentation](http://www.open3d.org/docs/latest/) (for `master` branch).

### My Question

Hello,
I appreciate the unbelievable effort you put into creating this amazing library !!

I succeeded running the [Color Map Optimization pipeline example](http://www.open3d.org/docs/latest/tutorial/pipelines/color_map_optimization.html?highlight=color%20map%20optimization) by calling **1. mesh, 2. camera_trajectory**, and **3. rgbd_images** of the fountain example.

## **Color Map Optimization with my custom dataset**
I was trying to color my own clay mesh by running the Color Map Optimization pipeline with my own dataset.
I already had rgb_images (photos of an object), mesh (3D reconstructed from the photos using SfM) and camera extrinsic/intrinsic information.

Thus,
1. I extracted depth images from the mesh using the camera information and mesh.
1.1. I referred to [the headless rendering tutorial.](http://www.open3d.org/docs/latest/tutorial/visualization/headless_rendering.html?highlight=headless%20rendering)
1.2. In this process, I have translated camera extrinsic/intrinsic information into camera_trajectory(.log file).

2. I ran [Color Map Optimization pipeline example](http://www.open3d.org/docs/latest/tutorial/pipelines/color_map_optimization.html?highlight=color%20map%20optimization) by calling my custom dataset's **1. mesh, 2. camera_trajectory**, and **3. rgbd_images**.

## **Problem**
My mesh is colored wrong. I double checked camera extrinsic/intrinsic information in the **2. camera_trajectory**, and it was consistent with the one that I used while extracting the depth images from the above process (**1.**).
The following figure illustrates our wrong colored mesh.
![image](https://user-images.githubusercontent.com/123041953/226522833-22a41e27-9f3c-4dbc-aaee-52f31cafed35.png)

I have no idea what is wrong, Please Help.
Thanks for your precious time.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.