Closed caiyongqi closed 7 months ago
Yes, it's transforming the SH coefficients from the camera coordinate system to the world coordinate system. The diff-gaussian-rasterization-modifed
code changes the convention for the spherical harmonics to match the e3nn library's conventions. This makes it possible to use the Wigner D matrices provided by e3nn to rotate the spherical harmonics. For more details, see this comment.
Is the following code transforming the predicted SH coefficients in the camera coordinate system to the world coordinate system?
https://github.com/dcharatan/pixelsplat/blob/f4ae9c1396ce62097b407e819321f5819d7788a9/src/model/encoder/common/gaussian_adapter.py#L90
In addition, the "diff-gaussian-rasterization-modified" only modifies the content related to the SH coefficient and has no effect on other parameters(scale, rotate...)?