Papers › Learning a model of facial shape and expression from 4D scans
Learning a model of facial shape and expression from 4D scans
Tianye Li, Timo Bolkart, Michael J. Black, Hao Li, Javier Romero
he field of 3D face modeling has a large gap between high-end and low-end methods. At the high end, the best facial animation is indistinguishablefrom real humans, but this comes at the cost of extensive manual labor. At the low end, face capture from consumer depth sensors relies on 3D face models that are not expressive enough to capture the variability in natural facial shape and expression. We seek a middle ground by learning a facial model from thousands of accurately aligned 3D scans. Our FLAME model (Faces Learned with an Articulated Model and Expressions) is designed to work with existing graphics software and be easy to fit to data. FLAME uses a linear shape space trained from 3800 scans of human heads. FLAME combines this linear shape space with an articulated jaw, neck, and eyeballs, pose-dependent corrective blendshapes, and additional global expression blendshapes. The pose and expression dependent articulations are learned from 4D face sequences in the D3DFACS dataset along with additional 4D sequences. We accurately register a template mesh to the scan sequences and make the D3DFACS registrations available for research purposes. In total the model is trained from over 33, 000 scans. FLAME is low-dimensional but more expressive than the FaceWarehouse model and the Basel Face Model. We compare FLAME to these models by fitting them to static 3D scans and 4D sequences using the same optimization method. FLAME is significantly more accurate and is available for research purposes.
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Face Reconstruction | NoW Benchmark | FLAME template | Mean Reconstruction Error (mm) | 1.53 | #9 of 17 | Archive leaderboard | report |
| 3D Face Reconstruction | NoW Benchmark | FLAME template | Median Reconstruction Error | 1.21 | #9 of 17 | Archive leaderboard | report |
| 3D Face Reconstruction | NoW Benchmark | FLAME template | Stdev Reconstruction Error (mm) | 1.31 | #9 of 17 | Archive leaderboard | report |
| Face Alignment | FaceScape | FLAME | NME | 0.341 | #3 of 4 | 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