Closed linkinSimon closed 2 years ago
Oh, I got it.
bbox_3d_size = 400 and bbox_3d_size_root = 400 is assuming a hand relative depth is within 400mm if the root lies at the middle 200 mm.
joint_coord[:,2] = (joint_coord[:,2] / (cfg.bbox_3d_size/2) + 1)/2. * cfg.output_hm_shape[0] link src is trying to map the relative depth to 0-64 space like the 2D heatmaps with the root joint lies at the middle 32.
A huge thanks for the explanation !!
- The size of a 3d box of a hand is 400 mm.
- To make it into a heatmap space. Thanks!
How do you decide the value of bbox_3d_size? The largest value in the dataset? If i training the model using my own dataset, how to set bbox_3d_size?
thanks
Best wishes
Just based on prior knowledge about human scales. The value does not belong to specific datasets
Hi, @mks0601,
Thanks for sharing this amazing project !! May I ask some questions about the transform_input_to_output_space function?
Why set bbox_3d_size = 400 and bbox_3d_size_root = 400 in (link src), what's the meaning of the two?
Why preprocess the ground truth relative depth into this domain joint_coord[:,2] = (joint_coord[:,2] / (cfg.bbox_3d_size/2) + 1)/2. * cfg.output_hm_shape[0] (link src), is this good for converge?
Is there any explanation in this paper or this repository that I missed?
Really thanks for your time and help!!