Shuo comments

Repositories
Issues
Comments

Results 24 comments of


                                            Shuo

Incorporating Known Camera Poses in Global Alignment Optimization

I think it is easy to pass some known camera poses to setting. During the optimization, the fixed poses are not passed to the optimizer, that would be OK.

How can I find the XYZ coordinates of a 3D point cloud corresponding to a pixel position in a 2D image?

In the alignment, I think you can get the pixel and the corresponding depth

Convert Output to COLMAP FORMAT

Here I provide a simple script to convert the result to the COLMAP format ```python import cv2 import os from pathlib import Path import open3d as o3d import numpy as...

Reconstruction has missing attributes

maybe you can tune the confidence ?