dldaisy
dldaisy
Dear authors, Thanks for the great work. I have a question about the below code. It seems that you have adapted the original code to implement naive hybrik. You change...
Training agora directly with current hmr pipeline would fail, since hmr didn't recenter 3d joints to 0 for agora dataset. Meanwhile, since smpl kid have 11 dimensions, which is not...
hello, I preprocess agora dataset(3840*2160 / smpl image using agora data converter, and use it to train HMR model. For the adversarial training part, I first replace the cmu_mosh with...
Hi, I run testing on wild images and found sometimes it will output extremely unnatural body mesh. Here is the input image:  And below are the screenshots of the...
Hi, I noticed that there is a layer named `decleaf` in the inference model: https://github.com/Jeff-sjtu/HybrIK/blob/e10afb149e10cf721b619b12eb81f02b7ad3c4e0/hybrik/models/simple3dposeBaseSMPL24.py#L109 which does not exist in training model simple3dposeBaseSMPL. When looking into the code, I found...
Hi, I'm trying to train the model from scratch on another dataset. I noticed that you get depth_factor from this line: ```depth_factor = np.array([self.bbox_3d_shape[2]]).astype(np.float32)``` I have 2 questions regarding depth_factor:...
Hi @williamSYSU, Thanks for the work. I found a potential bug in your seqgan rollout code. In the below code snippet in function `get_reward` in utils/rollout.py, ```python rewards = torch.zeros([rollout_num...
Hi, I'm trying to recover a smplx model from the saved params output by ExPose and overlay it on the original image. However, I noticed that there is a shift...
Hi, We found the `jaw` joint is not located on the jaw but is beside the head joint after visualizing the 55 joints on a mesh as shown below. May...