Award for Reproducing the Paper Results

cleardusk / 3DDFA_V2

The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

MIT License

2.92k stars 515 forks source link

Award for Reproducing the Paper Results #89

Open zcy8123878 opened 3 years ago

zcy8123878 commented 3 years ago

Hi,

If ANYONE succeeded in reproducing the paper results, you are welcome to send your training code along with your huobi wallet address to me via zcy8123878@gmail.com. After checking the results myself, I will send 0.3ETH(≈800$) to your wallet but only for the first provider : )

Thanks ~

lyyiangang commented 3 years ago

you'd better train your net on 3ddfa_v1, v2's pipeline is too complicated.

zcy8123878 commented 3 years ago

I have no difficulty in representing v1.0, however, I made much effort but failed to represent v2.0, some methods in the paper just didn't work well for me.

cleardusk commented 2 years ago

The benefit of meta-joint optimization is limited, more augmentation produces better results. If possible, using externel data (the paper only uses 300W-LP) may promote the generalization ability. @zcy8123878