You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When I follow "script/eval_ball_s.sh" for evaluation, I find that the image I get from rendering on the test set is wrong, as shown below. However the mesh obtained from training is basically correct and the position can be aligned with groundtruth. Therefore, I think the camera positions are correct.
I'm not sure if I have to complete the full training of stage1-3 before I can evaluate. Could you please provide a complete training and evaluation specific process for the new perspective synthesis in the README?
Thanks a lot,
The text was updated successfully, but these errors were encountered:
Dear Authors:
When I follow "script/eval_ball_s.sh" for evaluation, I find that the image I get from rendering on the test set is wrong, as shown below. However the mesh obtained from training is basically correct and the position can be aligned with groundtruth. Therefore, I think the camera positions are correct.
I'm not sure if I have to complete the full training of stage1-3 before I can evaluate. Could you please provide a complete training and evaluation specific process for the new perspective synthesis in the README?
Thanks a lot,
The text was updated successfully, but these errors were encountered: