Papers › Towards Metrical Reconstruction of Human Faces

Towards Metrical Reconstruction of Human Faces

13 Apr 2022arXiv:2204.06607archive 2025-07-28

Wojciech Zielonka, Timo Bolkart, Justus Thies

Face reconstruction and tracking is a building block of numerous applications in AR/VR, human-machine interaction, as well as medical applications. Most of these applications rely on a metrically correct prediction of the shape, especially, when the reconstructed subject is put into a metrical context (i.e., when there is a reference object of known size). A metrical reconstruction is also needed for any application that measures distances and dimensions of the subject (e.g., to virtually fit a glasses frame). State-of-the-art methods for face reconstruction from a single image are trained on large 2D image datasets in a self-supervised fashion. However, due to the nature of a perspective projection they are not able to reconstruct the actual face dimensions, and even predicting the average human face outperforms some of these methods in a metrical sense. To learn the actual shape of a face, we argue for a supervised training scheme. Since there exists no large-scale 3D dataset for this task, we annotated and unified small- and medium-scale databases. The resulting unified dataset is still a medium-scale dataset with more than 2k identities and training purely on it would lead to overfitting. To this end, we take advantage of a face recognition network pretrained on a large-scale 2D image dataset, which provides distinct features for different faces and is robust to expression, illumination, and camera changes. Using these features, we train our face shape estimator in a supervised fashion, inheriting the robustness and generalization of the face recognition network. Our method, which we call MICA (MetrIC fAce), outperforms the state-of-the-art reconstruction methods by a large margin, both on current non-metric benchmarks as well as on our metric benchmarks (15% and 24% lower average error on NoW, respectively).

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Zielon/MICA officialmentioned on GitHubpytorchNOASSERTION 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

2k3D Face ReconstructionFace RecognitionFace Reconstruction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Face Reconstruction NoW Benchmark MICA Mean Reconstruction Error (mm) 1.11 #2 of 17 Archive leaderboard report
3D Face Reconstruction NoW Benchmark MICA Median Reconstruction Error 0.90 #2 of 17 Archive leaderboard report
3D Face Reconstruction NoW Benchmark MICA Stdev Reconstruction Error (mm) 0.92 #2 of 17 Archive leaderboard report
3D Face Reconstruction REALY MICA @cheek 1.099 (±0.324) #19 of 24 Archive leaderboard report
3D Face Reconstruction REALY MICA @forehead 2.374 (±0.683) #19 of 24 Archive leaderboard report
3D Face Reconstruction REALY MICA @mouth 3.478 (±1.204) #19 of 24 Archive leaderboard report
3D Face Reconstruction REALY MICA @nose 1.585 (±0.325) #19 of 24 Archive leaderboard report
3D Face Reconstruction REALY MICA all 2.134 #19 of 24 Archive leaderboard report
3D Face Reconstruction REALY (side-view) MICA @cheek 1.109 (±0.325) #15 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) MICA @forehead 2.379 (±0.675) #15 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) MICA @mouth 3.567 (±1.212) #15 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) MICA @nose 1.525 (±0.322) #15 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) MICA all 2.145 #15 of 19 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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