Bingo_ang

@Luciano07 Thanks very much for your outputs and detailed suggestions! The key factor I think may be the way we get the depth map and color map without background. Can...

@LizhenWangT Thanks for your nice suggestion~ I wonder if you could release your team's source code for removing the background from color map and depth map?

@Luciano07 @LizhenWangT THANKS for your qiuck reply! I will have a try according to your suggestions~

@enriccorona Wonderful!! Thank you so much for your patient reply and instruction, that's what we SMPLicit's fans want~ I will have a try! Thanks again!

I met the same problem.

@lyzhenshuai Hi! I met the same problem. Have you solved it?

> I and my friends met the same problem, and we have no ways to solve it.

@kfarivar @ashwath98 @bharat-b7 Hi, all~ I ran the demo commands(using the pre-trained model "checkpoint_epoch_249.tar" in README), but met some problems: My input is a 3D scan, and the IPNet predictions(correspondences...

@ashwath98 Thanks very much for your quick and explicit reply! I agree that the method in your experiments will output better results, especially in some challenge views or poses~ **But...

@Daixinxin-cc Hi~ Maybe you have to do some preprocessing to your own 3D scan input: translate and rotate your input model, making sure that the 3D model's center is roughly...