# Joint Voxel and Coordinate Regression for Accurate 3D Facial Landmark Localization

arXiv: https://arxiv.org/abs/1801.09242 · HTML: https://mlsanity.com/paper/1801.09242/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jan 2018.

## Built on by (most cited first, 6 of 6)

- [DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Image](https://mlsanity.com/paper/2204.03688/) (2022)
- [SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction](https://mlsanity.com/paper/2106.03021/) (2021)
- [Few-shot Geometry-Aware Keypoint Localization](https://mlsanity.com/paper/2303.17216/) (2023)
- [FLNeRF: 3D Facial Landmarks Estimation in Neural Radiance Fields](https://mlsanity.com/paper/2211.11202/) (2022)
- [Location-guided Head Pose Estimation for Fisheye Image](https://mlsanity.com/paper/2402.18320/) (2024)
- [R2I-rPPG: A Robust Region of Interest Selection Method for Remote Photoplethysmography to Extract Heart Rate](https://mlsanity.com/paper/2410.15851/) (2024)

## Abstract (arXiv)

3D face shape is more expressive and viewpoint-consistent than its 2D counterpart. However, 3D facial landmark localization in a single image is challenging due to the ambiguous nature of landmarks under 3D perspective. Existing approaches typically adopt a suboptimal two-step strategy, performing 2D landmark localization followed by depth estimation. In this paper, we propose the Joint Voxel and Coordinate Regression (JVCR) method for 3D facial landmark localization, addressing it more effectively in an end-to-end fashion. First, a compact volumetric representation is proposed to encode the per-voxel likelihood of positions being the 3D landmarks. The dimensionality of such a representation is fixed regardless of the number of target landmarks, so that the curse of dimensionality could be avoided. Then, a stacked hourglass network is adopted to estimate the volumetric representation from coarse to fine, followed by a 3D convolution network that takes the estimated volume as input and regresses 3D coordinates of the face shape. In this way, the 3D structural constraints between landmarks could be learned by the neural network in a more efficient manner. Moreover, the proposed pipeline enables end-to-end training and improves the robustness and accuracy of 3D facial landmark localization. The effectiveness of our approach is validated on the 3DFAW and AFLW2000-3D datasets. Experimental results show that the proposed method achieves state-of-the-art performance in comparison with existing methods.