Closed ricshaw closed 1 year ago
Did you use the mask loss? The mask loss should remove the floating artifacts around the human.
Yes I used the same config file as NHR sport1. mask_weight is set to 0.1, maybe I should increase it? I also set the following: face_sample_ratio = 0.0 body_sample_ratio = 1.0 Because I don’t have the face segmentation. Is that okay?
Hi. You can try to set body_sample_ratio = 0.7 as in the config file of NHR sport1 for body_sample_ratio = 1.0 means all sampled rays are on foreground objects. You can read this part of the code for more detail https://github.com/zju3dv/mlp_maps/blob/7fda4ac19e84692f1070614f669e44080541bf2b/lib/utils/if_nerf/if_nerf_data_utils.py#L172
Ah that might help, I will try that! I had another question about fixedcameras in the config file. I set fixedcameras to be 3 random training views… What does fixedcameras mean?
It follows Neural Volumes, which takes some fixed subviews as the input of the encoder. Please read the paper of Neural Volumes.
Thank you!
Hi, thank you for the code and great work. However, I am having issues using my own data. My result after training for 200 epochs is shown below:
Prediction:![frame0010_view0018](https://github.com/zju3dv/mlp_maps/assets/9107279/d462559b-7724-4979-bcd8-51ae29a20f84)
Groundtruth:![frame0010_view0018_gt](https://github.com/zju3dv/mlp_maps/assets/9107279/e8fa37bd-2c52-4a20-ba03-6d84a9db212f)
I am using an edited version of the sport1 nhr dataloader and following the config file from: python train_net.py --config configs/nhr/sport1.py
Do you know why this is not working for my data? The dataset consists of 72 cameras, I am using 100 frames, and I have fit SMPL vertices to all views as shown below:![smpl](https://github.com/zju3dv/mlp_maps/assets/9107279/b70a8b57-d59a-4a89-be5f-8798d7331e18)