Hi, great work. Have two ideas and would like to ask if they are feasible:
Is it possible to input the pose of each image instead of relying on the algorithm to predict it? Sometimes there may be better algorithms or other sensors to assist in predicting the pose of each input image, such as feature extraction and matching based on deep learning, lidar-aided pose calculation, etc.
Supposing the position at timestamp $t_0$ and $t_n$ are near, is the radiance field optimizing at $t_n$ the same as the radiance field at $t_0$? If not, is it feasible to optimize the same radiance field?
I know the current code may not support the above features. Just want to ask if the above two ideas conflict with the existing algorithm framework and whether they are theoretically feasible?
Yes, with_preprocessed_poses 1 --lr_R_init 0 --lr_t_init 0 disables pose optimization and loads camera parameters from ${SCENE_DIR}/transforms.json.
This should be feasible. However, it will likely require some loop closure detection as some pose drift may occur with the current local pose estimation.
Hi, great work. Have two ideas and would like to ask if they are feasible:
I know the current code may not support the above features. Just want to ask if the above two ideas conflict with the existing algorithm framework and whether they are theoretically feasible?