Papers › Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network
Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network
Anh Tuan Tran, Tal Hassner, Iacopo Masi, Gerard Medioni
The 3D shapes of faces are well known to be discriminative. Yet despite this, they are rarely used for face recognition and always under controlled viewing conditions. We claim that this is a symptom of a serious but often overlooked problem with existing methods for single view 3D face reconstruction: when applied "in the wild", their 3D estimates are either unstable and change for different photos of the same subject or they are over-regularized and generic. In response, we describe a robust method for regressing discriminative 3D morphable face models (3DMM). We use a convolutional neural network (CNN) to regress 3DMM shape and texture parameters directly from an input photo. We overcome the shortage of training data required for this purpose by offering a method for generating huge numbers of labeled examples. The 3D estimates produced by our CNN surpass state of the art accuracy on the MICC data set. Coupled with a 3D-3D face matching pipeline, we show the first competitive face recognition results on the LFW, YTF and IJB-A benchmarks using 3D face shapes as representations, rather than the opaque deep feature vectors used by other modern systems.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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 | Florence | 3DMM-CNN | Average 3D Error | 1.93 | #7 of 16 | Archive leaderboard | report |
| 3D Face Reconstruction | Florence | Tran et al. | RMSE Cooperative | 1.97 | #15 of 16 | Archive leaderboard | report |
| 3D Face Reconstruction | Florence | Tran et al. | RMSE Indoor | 2.03 | #15 of 16 | Archive leaderboard | report |
| 3D Face Reconstruction | Florence | Tran et al. | RMSE Outdoor | 1.93 | #15 of 16 | Archive leaderboard | report |
| 3D Face Reconstruction | NoW Benchmark | 3DMM-CNN | Mean Reconstruction Error (mm) | 2.33 | #17 of 17 | Archive leaderboard | report |
| 3D Face Reconstruction | NoW Benchmark | 3DMM-CNN | Median Reconstruction Error | 1.84 | #17 of 17 | Archive leaderboard | report |
| 3D Face Reconstruction | NoW Benchmark | 3DMM-CNN | Stdev Reconstruction Error (mm) | 2.05 | #17 of 17 | Archive leaderboard | report |
| Face Verification | YouTube Faces DB | 3DMM face shape parameters + CNN | Accuracy | 88.80% | #12 of 12 | 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.
Methods
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