PinataFarms / DAD-3DHeads

Official repo for DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image (CVPR 2022).
Other
450 stars 42 forks source link

From scratch train the model with custom dataset. #20

Open hewumars opened 1 year ago

hewumars commented 1 year ago

I use fit_scan.py to generate my custom dataset.

after train 500 epoch, to test image, 2d vertices are close to ok, but 3d vertices are not correct at all.

What is the possible reason for this?

17-uidq0657-2021-8-12-195100_my_image_0_51_68_landmarks 17-uidq0657-2021-8-12-195100_my_image_0_51_445_landmarks 17-uidq0657-2021-8-12-195100_my_image_0_51_face_mesh

17-uidq0657-2021-8-12-195100_my_image_0_51 vertices unit is millimeters. label json is as follows: { "vertices": [ [ 0.04518344467567696, 0.17775802332478438, -0.39643736129255214 ], [ 0.048658336279237865, 0.1768529119593747, -0.39521232999733014 ], [ 0.04945889770001125, 0.17799078430798437, -0.39566139249431254 ], [ 0.04600878696145669, 0.17851796093268812, -0.39655851551505694 ], [ 0.049867298790216646, 0.18126493109592973, -0.3838844547280212 ], [ 0.05354209709941608, 0.18278256826344497, -0.3882279945523791 ], ........

], "model_view_matrix": [ [ 0.9792482433597487, 0.0477148473832626, 0.19696743694336385, 0.28946250677108765 ], [ -0.0029217173213029147, 0.9751122033902291, -0.22169270255772225, -0.300279438495636 ], [ -0.2026433849024943, 0.2165167063730747, 0.9550163215446188, 1.0343986749649048 ], [ 0.0, 0.0, 0.0, 1.0 ] ], "projection_matrix": [ [ 1373.6173986936753, 0.0, -252.10671060735615, 0.0 ], [ 0.0, 1372.9339350792657, 356.03684183339647, 0.0 ], [ 0.0, 0.0, 1, -0.2 ], [ 0.0, 0.0, 1, 0.0 ] ] }

Ding2Zhen commented 10 months ago

https://github.com/PinataFarms/DAD-3DHeads/issues/18