[bhouston]

I think you needed more time and a more sophisticated approach. One could have used a 3D scanner and acquired the body shape and then one could parameterize it and then figure out the deformation you want to achieve from the bra -- even preview it for the customer, where do they want things to end up, and how much stress that will put on their body -- and then one could figure out the patterns to make again from the contact areas you wanted.

Basically it is a 3D problem and I think you didn't take a sophisticated approach because you are likely not knowledgable in that area.

You tried to apply tailoring to it, but tailoring is not body fitting nor shape changing as a bra is, nor is tailoring about stresses and weight distribution (which is comfort.)

It is a solvable problem, but your approach was not the correct one, it was simplistic.

It is an incredibly interesting problem though.

[ISOcGAxAgO]

I agree with your take on this. Facebook has done considerable work with their Detectron / Dense Pose projects which can UV unwrap human bodies using AI. (https://github.com/facebookresearch/DensePose) Another is the smpl / smplify-x project (https://github.com/vchoutas/smplify-x)

Further, by utilizing generated (synthetic) data with 3d scanned human models, or generating your own with something like makehuman or daz3D, you should be able to find a way to UV unwrap a distorted sphere. I've had a lot of success with generating synthetic data like this with Blender 3D and training various neural networks (Mask RCNN / Deeplab for example) with various combinations of this synthetic and real datasets.

[erichocean]

Yup, they have the wrong tech approach. Good they stopped wasting money though…