Papers › MPF-GAN: an enhanced architecture for 3D face reconstruction
MPF-GAN: an enhanced architecture for 3D face reconstruction
Mehdi Malah, Fayçal Abbas, Ramzi Agaba, Dalal Bardou, Mohamed Chaouki Babahenini
In this article, we address the challenge of accurate 3D face reconstruction by proposing an enhanced architecture. We observe that using a single error calculation formula for the entire face leads to precise reconstruction of certain parts at the expense of others, particularly the eyes and mouth. We introduce a multi-task learning approach to address this issue, allowing our model to train on multiple data types. We propose a new analytical solution for mouth shape identification and its integration into the loss function optimization process. This solution resolves a problem that was often difficult to model in previous works accurately and has demonstrated improved reconstruction performance. In our research, we have also created and made available a new dataset for 3D face reconstruction. This dataset is unique as it focuses on different facial parts. The results show that our multi-task learning approach significantly improves the loss function for delicate facial parts, thus enhancing the quality of reconstruction in these specific areas. The code and data are publicly available on the project’s link: https://mpf-gan.github.io
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections