DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment

Sensitivity to severe occlusion and large view angles limits the usage scenarios of the existing monocular 3D dense face alignment methods. The state-of-the-art 3DMM-based method, directly regresses the model's coefficients, underutilizing the low-level 2D spatial and semantic information, which can actually offer cues for face shape and orientation. In this work, we demonstrate how modeling 3D facial geometry in image and model space jointly can solve the occlusion and view angle problems. Instead of predicting the whole face directly, we regress image space features in the visible facial region by dense prediction first. Subsequently, we predict our model's coefficients based on the regressed feature of the visible regions, leveraging the prior knowledge of whole face geometry from the morphable models to complete the invisible regions. We further propose a fusion network that combines the advantages of both the image and model space predictions to achieve high robustness and accuracy in unconstrained scenarios. Thanks to the proposed fusion module, our method is robust not only to occlusion and large pitch and roll view angles, which is the benefit of our image space approach, but also to noise and large yaw angles, which is the benefit of our model space method. Comprehensive evaluations demonstrate the superior performance of our method compared with the state-of-the-art methods. On the 3D dense face alignment task, we achieve 3.80% NME on the AFLW2000-3D dataset, which outperforms the state-of-the-art method by 5.5%. Code is available at https://github.com/lhyfst/DSFNet.

PDF Abstract CVPR 2023 PDF CVPR 2023 Abstract

Datasets


Results from the Paper


 Ranked #1 on 3D Face Reconstruction on AFLW2000-3D (Mean NME metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Head Pose Estimation AFLW2000 DSFNet-f MAE 3.25 # 1
3D Face Reconstruction AFLW2000-3D DSFNet-is Mean NME 3.16 # 1
Face Alignment AFLW2000-3D DSFNet-f Mean NME 3.8 # 1

Methods


No methods listed for this paper. Add relevant methods here