Dynamic Neural Radiance Fields for Monocular 4D Facial Avater Reconstruction
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
12138wzm opened this issue 2 years ago · comments
Thanks for your wonderful work!
When tested using eval_transformed_rays.py, I got images have clearly visible pixels. As shown in the figure below. The model was trained 400K times. The configuration file is dave_DVP_lcode_fixed_bg_256_paper_model.yml.
eval_transformed_rays.py
dave_DVP_lcode_fixed_bg_256_paper_model.yml
What can I do to get clear generated images?
When I modified validation.num_coarse and validation.num_fine from 16 to 64 in dave_DVP_lcode_fixed_bg_256_paper_model.yml, the results are fine.
validation.num_coarse
validation.num_fine