search

YuelangX / Multiview-3DMM-Fitting

Fitting 3DMM models to multiview (monocular) video data.
MIT License
59 stars 10 forks source link

what FLAME version did you use? #2

Closed xiyichen closed 2 months ago

xiyichen commented 2 months ago

Thanks for the work and code release! I tested it on a custom multi-view dataset with ground truth camera parameters. Using the BFM model, I am able to get desired results, but using FLAME 2020 (with the same camera parameters and landmarks), the resulted mesh looks very distorted. BFM result: vis_1_bfm FLAME result: vis_1_flame

I wonder if you used a different FLAME version. I also tried 2019 but it's also not working.

YuelangX commented 2 months ago

The default parameter setting is for FLAME 2017. Maybe you can simply try to modify the weight of regular loss to get better results.

xiyichen commented 2 months ago

Increasing both regularization weights to 1e-5 indeed solves the problem. Thank you!