西行寺幽幽子的狗
西行寺幽幽子的狗
8.9 Edit [My code. ](https://github.com/ZCWzy/preprocessForHugs?tab=readme-ov-file) I wrote my own data preprocessing module and it seems to work. I seem to have succeeded in using 4D-humans to completely replace ROMP ,...
> 您是否能够解决此问题并使用自己的数据来训练人类？ @yashgarg98 no, There is still a problem with the global_orient parameter.
@TCN1214 The body_pose in **4D-humans** is a rotation matrix representation and the body_pose in **smpl_optimized_aligned_scale.npz** is an axis angle representation (Axis with angle magnitude). A similar question was asked in...
> @ZCWzy, got it, thanks! And may I know if you also get the **global_orient** and **betas** from **4D Human**? I noticed that in smpl_optimized_aligned_scale.npz , the **betas** are the...
> > **4d-Humans** tracking is demonstrated with the help of [**PHALP**.](https://github.com/brjathu/PHALP) The bbox, global_orient, body_pose and betas can be obtained directly using **PHALP**. But there's a problem with global_orient in...
@TCN1214   I think transl is getting it from here. ~I verified it using blender.（Transform the original vertices using the scale and transl I calculated, it is only a...
> > I think transl is getting it from here. > > ~I verified it using blender.（Transform the original vertices using the scale and transl I calculated, it is only...
> > for vert, vertInWorld, scale, translation, go in zip(verts, vertsInWorld, scales, translations, pose): > > vertWithoutRotation = vert*scale +translation > > ``` > > rotation = open3d_registration(vertWithoutRotation, vertInWorld) >...
@TCN1214 do not use that way to create global_orient, it may not accurent. use this: ``` def solve_transformation(verts, j3d, j2d, plane_model, colmap_cap, smpl_cap): np.set_printoptions(suppress=True) mvp = np.matmul(smpl_cap.intrinsic_matrix, smpl_cap.extrinsic_matrix) trans =...
> > But it would make the > > `assert x.max() = -EPS, f "x must be in [0, 1], got {x.min()} and {x.max()}"` > > (from /hugs/models/models/triplane.py) > >...