mlsanityData to 14 Oct 2026

Towards 3D Face Reconstruction in Perspective Projection: Estimating 6DoF Face Pose from Monocular Image

arXiv 2205.04126 ↗First posted 9 May 2022cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

In 3D face reconstruction, orthogonal projection has been widely employed to substitute perspective projection to simplify the fitting process. This approximation performs well when the distance between camera and face is far enough. However, in some scenarios that the face is very close to camera or moving along the camera axis, the methods suffer from the inaccurate reconstruction and unstable temporal fitting due to the distortion under the perspective projection. In this paper, we aim to address the problem of single-image 3D face reconstruction under perspective projection. Specifically, a deep neural network, Perspective Network (PerspNet), is proposed to simultaneously reconstruct 3D face shape in canonical space and learn the correspondence between 2D pixels and 3D points, by which the 6DoF (6 Degrees of Freedom) face pose can be estimated to represent perspective projection. Besides, we contribute a large ARKitFace dataset to enable the training and evaluation of 3D face reconstruction solutions under the scenarios of perspective projection, which has 902,724 2D facial images with ground-truth 3D face mesh and annotated 6DoF pose parameters. Experimental results show that our approach outperforms current state-of-the-art methods by a significant margin. The code and data are available at https://github.com/cbsropenproject/6dof_face.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 29 of its 61 references that are in the map. First posted on arXiv 9 May 2022.

Builds on

29 of 61 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 525
  6. 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 482
  7. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  8. 2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 255
  9. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  10. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  11. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  12. 2020FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Predictioncited by 196
17 more
  1. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  2. 2019Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervisioncited by 176
  3. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  4. 2017Fine-Grained Head Pose Estimation Without Keypointscited by 163
  5. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
  6. 2018Face Alignment in Full Pose Range: A 3D Total Solutioncited by 148
  7. 2022FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Datasetcited by 98
  8. 2020AvatarMe: Realistically Renderable 3D Facial Reconstruction "in-the-wild"cited by 91
  9. 2020img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimationcited by 58
  10. 2021AvatarMe++: Facial Shape and BRDF Inference with Photorealistic Rendering-Aware GANscited by 49
  11. 2020A Vector-based Representation to Enhance Head Pose Estimationcited by 35
  12. 2014Multilinear Wavelets: A Statistical Shape Space for Human Facescited by 32
  13. 2021Riggable 3D Face Reconstruction via In-Network Optimizationcited by 31
  14. 2017Dense Face Alignmentcited by 24
  15. 2017FacePoseNet: Making a Case for Landmark-Free Face Alignmentcited by 21
  16. 2019Learning Perspective Undistortion of Portraitscited by 14
  17. 2018MobileFace: 3D Face Reconstruction with Efficient CNN Regressioncited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 2; 2026: 1.

9 papers.

  1. 20233D Face Reconstruction with the Geometric Guidance of Facial Part Segmentationcited by 38
  2. 2024S2TD-Face: Reconstruct a Detailed 3D Face with Controllable Texture from a Single Sketchcited by 5
  3. 2024Semi-Supervised Unconstrained Head Pose Estimation in the Wildcited by 2
  4. 2025SRM-Hair: Single Image Head Mesh Reconstruction via 3D Morphable Haircited by 2
  5. 2024Recent Advancement in 3D Biometrics using Monocular Cameracited by 1
  6. 2024Bidirectional Regression for Monocular 6DoF Head Pose Estimation and Reference System Alignmentcited by 0
  7. 2024An End-to-End Depth-Based Pipeline for Selfie Image Rectificationcited by 0
  8. 2025EditIQ: Automated Cinematic Editing of Static Wide-Angle Videos via Dialogue Interpretation and Saliency Cuescited by 0
  9. 2026VGGT-HPE: Reframing Head Pose Estimation as Relative Pose Predictioncited by 0