A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimization
Abstract: 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 publicly available if accepted.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: - We have newly added ablation experiment to support the effectiveness of our EM-style NeuFace optimization (Appendix Sec. B and Table S3).
- We have added additional statistics related to our dataset (Table 1 and Appendix Sec. A.).
- We have added additional discussion about the experiment (Sec. 6).
- We have revised and re-ordered the writing following the reviews.
Assigned Action Editor: ~Antoni_B._Chan1
Submission Number: 2208
Loading