Papers › Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regression

Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regression

15 Aug 2022arXiv:2208.07142archive 2025-07-28

Jia Guo, Jinke Yu, Alexandros Lattas, Jiankang Deng

Even though 3D face reconstruction has achieved impressive progress, most orthogonal projection-based face reconstruction methods can not achieve accurate and consistent reconstruction results when the face is very close to the camera due to the distortion under the perspective projection. In this paper, we propose to simultaneously reconstruct 3D face mesh in the world space and predict 2D face landmarks on the image plane to address the problem of perspective 3D face reconstruction. Based on the predicted 3D vertices and 2D landmarks, the 6DoF (6 Degrees of Freedom) face pose can be easily estimated by the PnP solver to represent perspective projection. Our approach achieves 1st place on the leader-board of the ECCV 2022 WCPA challenge and our model is visually robust under different identities, expressions and poses. The training code and models are released to facilitate future research.

PaperPDFCode

Code

deepinsight/insightface officialmentioned in papermentioned on GitHubpytorch report
bovifocr/insightface mentioned on GitHubpytorch report
pedrobvidal/insightface mentioned on GitHubpytorch report
yangyucheng000/-insightface mentioned on GitHubpytorchMIT report

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

3D Face ReconstructionFace Reconstructionregression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

PnP

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