Shuo
For the SLAM system, I wonder how to maintain the scale consistently, especially when the scene changes (like from outdoor to indoor)
> This is really helpful! I've gotten further than before. > > ``` > > /home/relh/Code/???????????/dust3r/dust3r/cloud_opt/init_im_poses.py(61)init_from_known_poses() > 60 assert known_poses_msk[n] > ---> 61 _, i_j, scale = best_depthmaps[n] > 62...
I think `self.im_poses` is just as the name points, the estimated camera poses for each image in the global coordinate. The `self.pw_poses` is the estimated transformation of each prediction pair...
> If that is the case, wouldnt the estimated camera pose and estimated transformation be related? If `self.pw_poses` is the transformation of points in cam1 coordinates of each pair to...
Hi, I wonder when you say "I noticed that doing so did not result in any explicit errors", do you mean the predicted point map?
Which paper mentionds the disturbances of PE? Will it also affect RoPe?
what do you mean `layered`?
@lahavlipson By the way, I think there is a minor error when saving the camera intrinsic parameter here: In the [COLMAP doc](https://colmap.github.io/format.html#:~:text=%23%20%20%20CAMERA_ID%2C%20MODEL%2C%20WIDTH%2C%20HEIGHT%2C%20PARAMS%5B%5D), when saving the camera parameters should be ```...
specify the cuda arch: `cmake .. -DCMAKE_CUDA_ARCHITECTURES=89`
> Right now, the sparse global alignement is hit or miss, we are still working on it. You can try putting matching_conf_thr to 0, it was meant to help with...