A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimization
This work addresses the problem of creating high-quality 3D face annotations for videos, which is significant for researchers in computer vision and graphics, though it is incremental as it builds on existing 3D face reconstruction methods.
The authors tackled the challenge of generating reliable 3D face labels for in-the-wild dynamic videos by proposing NeuFace, a neural re-parameterized optimization method that annotates per-view/-frame accurate and consistent face meshes on large-scale videos, resulting in the NeuFace-dataset and demonstrating improved reconstruction accuracy and learning of 3D facial motion prior.
We propose NeuFace, a 3D face mesh pseudo annotation method on videos via neural re-parameterized optimization. Despite the huge progress in 3D face reconstruction methods, generating reliable 3D face labels for in-the-wild dynamic videos remains challenging. Using NeuFace optimization, we annotate the per-view/-frame accurate and consistent face meshes on large-scale face videos, called the NeuFace-dataset. We investigate how neural re-parameterization helps to reconstruct image-aligned facial details on 3D meshes via gradient analysis. By exploiting the naturalness and diversity of 3D faces in our dataset, we demonstrate the usefulness of our dataset for 3D face-related tasks: improving the reconstruction accuracy of an existing 3D face reconstruction model and learning 3D facial motion prior. Code and datasets will be available at https://neuface-dataset.github.io.