Hierarchical MLANet: Multi-level Attention for 3D Face Reconstruction From Single Images
This addresses the problem of accurate 3D face modeling from 2D images for computer vision applications, but it is incremental as it builds on existing methods like 3DMM and attention mechanisms.
The paper tackles 3D face reconstruction from single in-the-wild images by proposing Hierarchical MLANet, which uses multi-level attention mechanisms and semi-supervised training, achieving competitive results on benchmark datasets like AFLW2000-3D and MICC Florence.
Recovering 3D face models from 2D in-the-wild images has gained considerable attention in the computer vision community due to its wide range of potential applications. However, the lack of ground-truth labeled datasets and the complexity of real-world environments remain significant challenges. In this chapter, we propose a convolutional neural network-based approach, the Hierarchical Multi-Level Attention Network (MLANet), for reconstructing 3D face models from single in-the-wild images. Our model predicts detailed facial geometry, texture, pose, and illumination parameters from a single image. Specifically, we employ a pre-trained hierarchical backbone network and introduce multi-level attention mechanisms at different stages of 2D face image feature extraction. A semi-supervised training strategy is employed, incorporating 3D Morphable Model (3DMM) parameters from publicly available datasets along with a differentiable renderer, enabling an end-to-end training process. Extensive experiments, including both comparative and ablation studies, were conducted on two benchmark datasets, AFLW2000-3D and MICC Florence, focusing on 3D face reconstruction and 3D face alignment tasks. The effectiveness of the proposed method was evaluated both quantitatively and qualitatively.