Ailing Zeng
Ailing Zeng
Hi @jin-s13 , Not ready. I will update the API to use the model soon.
As shown in the training part, you need to assign a window size to train the SmoothNet. To test a SmoothNet, you must set the corresponding window size. `python train_smoothnet.py...
Hi @jinfagang, Actually, Hybrik is a model to estimate SMPL. The performance of Hybrik depends on the train and test sets. If your data is fast-moving and with high errors...
Yes, SmoothNet is a temporal-only model, which shares weights across spatial dimensions (any dimensions can be smoothed in parallel). There is no need to set the config of spatial dimensions.
Hi @jinfagang, We have not tested SmoothNet for the camera transition. Could you please try it on the rotation matrix and give us feedback?
Hi @squidward2021, Thanks for your interest! Could you please explain what the actual usage is?
Sure. Table 2 in the main paper shows the results of smoothing 2d poses.
Hi @jinfagang, since SmoothNet can generalize well across backbones, we suggest you can simply use the pre-trained models to test the output poses from ROMP. Looking forward to your further...
Actually, any pre-trained models can be used. Their differences are from the training dataset and backbones. For example, if you need to smooth on 3DPW, it will be better to...
Yes, make sure the input of SmoothNet is a continuous representation (e.g., 6d rotation matrix). The transformation function can be found here: https://github.com/cure-lab/SmoothNet/blob/main/lib/utils/geometry_utils.py#L35.