test issue on my own data

LizhenWangT / NormalGAN

NormalGAN: Learning Detailed 3D Human from a Single RGB-D Image (ECCV 2020)

72 stars 13 forks source link

test issue on my own data #4

Open ucaswindlike opened 3 years ago

ucaswindlike commented 3 years ago

Great work! I am tring to get the mesh of my pictures taken by ipad Lidar. https://developer.apple.com/forums/thread/663995.I get the intrinsics here,but I could not get the right mesh, the images in result/cz0,cz1,dz0,dz1 are all incorrect. when I test your data, the result is correct.https://developer.apple.com/forums/thread/663995

LizhenWangT commented 3 years ago

Thank you for your interest! As our pretrained network is specific on Kinect v2 instrinsics, I think it won't perform very well on your Lidar (your intrinsics is quite different). If you insist on the test, the cropped input resolution of our network should be (424 x 424), and check if you put your mask image in the right folder. And you'd better align the RGB image to depth image, rather than the inverse projection in https://developer.apple.com/forums/thread/663995.