Learningm
Learningm
Same question during reading this part, how to implement it in a training-free manner? Is it using mv-dream's multi-view block to replace the original 2d attention block in controlnet ?...
@Tuich Not quite sure, it seems replacing the multi-view block is not enough, since we need to keep the latent space embedding from controlnet same as origin.
Did you solve it? I came across same OOM problem.
I already set to 2, but still came across OOM. it seems that it need to setup higher value? accum_steps: 2 # We did not use gradient accumulation in our...
> 1. The loss curve largely depends on your training set. While, I would suggest visualizing using a higher smoothness value in tensorboard. > 2. Yeah the loss should be...
> Hi [@Learningm](https://github.com/Learningm) I know this is an old issue but have you figured out after computing the 9 2D keypoints, how they were lifted to 3D space using EPnP...
@Mechazo11 I'm afraid that i can not make some comments about your approach, cause i have moved to other topics instead of focusing this direction. https://github.com/NVlabs/FoundationPose, as far as i...