Thank you very much for your work!
Taking ewer as an example, I re-use nvdifmodeling to load and render the exported mesh. The code is as follows:
`
eye = [0.5, 0.0, 3.0]
up = np.array([0.0, 1.0, 0.0])
at = np.array([0, 0, 0])
a_mv = util.lookAt(eye, at, up)
a_mvp = np.matmul(proj_mtx, a_mv).astype(np.float32)[None, ...]
a_lightpos = np.linalg.inv(a_mv)[None, :3, 3]
a_campos = np.linalg.inv(a_mv)[None, :3, 3]
`
It ensures that all parameters are consistent, but it is found that the rendered image result after import is far from the final result during training:
Using the same code, I imported the original ewer's obj, and the rendered image is as follows, which proves that there is no problem with the super-parameter setting:
Thank you very much for your work! Taking ewer as an example, I re-use nvdifmodeling to load and render the exported mesh. The code is as follows: ` eye = [0.5, 0.0, 3.0] up = np.array([0.0, 1.0, 0.0]) at = np.array([0, 0, 0]) a_mv = util.lookAt(eye, at, up) a_mvp = np.matmul(proj_mtx, a_mv).astype(np.float32)[None, ...] a_lightpos = np.linalg.inv(a_mv)[None, :3, 3] a_campos = np.linalg.inv(a_mv)[None, :3, 3]
` It ensures that all parameters are consistent, but it is found that the rendered image result after import is far from the final result during training:![image](https://user-images.githubusercontent.com/17697877/217476563-bb00210c-5767-4ac1-801f-0a8a0faea1a2.png)
Using the same code, I imported the original ewer's obj, and the rendered image is as follows, which proves that there is no problem with the super-parameter setting:![image](https://user-images.githubusercontent.com/17697877/217476990-6ade221b-8961-466c-bb92-f2f7447bc36d.png)
What is the reason for this problem?