MonoRec
MonoRec copied to clipboard
Brummi
Official implementation of the paper: MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera (CVPR 2021)
Following are the proposed changes: [Fix 1](https://github.com/Brummi/MonoRec/commit/2d46273196306659f41ef3921727ece6d5791df1): Masking of the depth from a given roi had a mistake in the [ply_utils.py](https://github.com/Brummi/MonoRec/compare/main...hardik01shah:MonoRec:main#diff-712b0e42e4b8959dc0ae59ab6dfa355279062c21eb555f74604365a434886f12) file [Fix 2](https://github.com/Brummi/MonoRec/commit/51bdbdc2c3c2f883563b594e60f837ee1c9e1d9e): Parameter for mask_module checkpoint location in...
`pixel2cam` and `DepthWrapper` are not defined at `depthmap_to_points` function, fix it by kornia modules import.
Hi: Thank you for sharing this amazing work! I tried to train the model several times but the mask module bootstrapping can not converge on the KITTI dataset. The only...
Hi Felix, do you have any script to do some inference for personal dataset? Thanks!
Hi Felix, https://github.com/Brummi/MonoRec/blob/b2b3decc130d9ca333d1350096b9838a12f977a3/model/loss_functions/monorec_loss.py#L334 https://github.com/Brummi/MonoRec/blob/b2b3decc130d9ca333d1350096b9838a12f977a3/model/loss_functions/monorec_loss.py#L339 you use the .detach() method in the sdl at depth_refinement_loss, which cut the backpropagation, different from the depth_refinement_loss in the paper. Or did I misunderstand?
I have tested the code mentioned in issue #20 to produce colored pointcloud
Hello author, I have read this paper of yours and am very interested in your work, especially the visualization of point clouds, I would like to ask how you achieved...
