YuelangX / AvatarMAV

A PyTorch implementation of "AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxels"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Evaluation Metrics

solangii opened this issue · comments

I'd like to start by expressing my gratitude for your great work! While examining the codebase, I noticed that there is a lack of implementation for several key quantitative evaluation metrics, specifically PSNR, MSE, SSIM, and LPIPS. These metrics are pivotal for a comprehensive performance assessment and comparison against other methods.

Could you consider adding the above metrics to the repository?

If there's a specific reason these metrics were excluded or if there's a way to evaluate them with the existing code that I might have overlooked, please guide me accordingly.

Thank you for your attention to this request. I look forward to hearing from you soon. 😀