search

walsvid / Pixel2MeshPlusPlus

Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation. In ICCV2019.
https://arxiv.org/abs/1908.01491
BSD 3-Clause "New" or "Revised" License
356 stars 56 forks source link

Camera Parameters #9

Closed nitish11 closed 4 years ago

nitish11 commented 4 years ago

What are the values in the camera parameters? How to define these values for any new test case? For example, if I have 3 images of an object from different view points, how to define camera.txt?

walsvid commented 4 years ago

Hi @nitish11 , the camera parameters consists of numbers, e.g. 222.956664706 28.6626066017 0 0.926673522361 25. The meaning of each lines in file rendering_metadata.txt: from the left, they are azimuth, elevation, in-plane rotation, distance, the field of view. (in-plane rotation is always zero in ShapeNet dataset. ) For el-az system you can refer to the wiki https://en.wikipedia.org/wiki/Horizontal_coordinate_system.

For training in other data sets, I suggest using a method that can calibrate the extrinsic matrix of the camera such as colmap or other methods. In fact, it is unnecessary to use the el-az system. In our code we using extrinsic (R and t) in the end.