mlsanityData to 7 Oct 2026

BabyNet: Reconstructing 3D faces of babies from uncalibrated photographs

arXiv 2203.05908 ↗First posted 11 Mar 2022cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We present a 3D face reconstruction system that aims at recovering the 3D facial geometry of babies from uncalibrated photographs, BabyNet. Since the 3D facial geometry of babies differs substantially from that of adults, baby-specific facial reconstruction systems are needed. BabyNet consists of two stages: 1) a 3D graph convolutional autoencoder learns a latent space of the baby 3D facial shape; and 2) a 2D encoder that maps photographs to the 3D latent space based on representative features extracted using transfer learning. In this way, using the pre-trained 3D decoder, we can recover a 3D face from 2D images. We evaluate BabyNet and show that 1) methods based on adult datasets cannot model the 3D facial geometry of babies, which proves the need for a baby-specific method, and 2) BabyNet outperforms classical model-fitting methods even when a baby-specific 3D morphable model, such as BabyFM, is used.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 38 of its 84 references that are in the map. First posted on arXiv 11 Mar 2022.

Builds on

38 of 84 references.

References · 38

  1. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  2. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  3. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  4. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  5. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  6. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
  7. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  8. 2017CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filterscited by 203
  9. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  10. 2019Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervisioncited by 176
  11. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  12. 2018Nonlinear 3D Face Morphable Modelcited by 157
26 more
  1. 2019GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstructioncited by 150
  2. 2018Face Alignment in Full Pose Range: A 3D Total Solutioncited by 147
  3. 2018Unsupervised Training for 3D Morphable Model Regressioncited by 99
  4. 2019Towards High-fidelity Nonlinear 3D Face Morphable Modelcited by 91
  5. 2019Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generationcited by 89
  6. 2017Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regressioncited by 66
  7. 20163D Face Reconstruction by Learning from Synthetic Datacited by 64
  8. 2017Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translationcited by 56
  9. 2020Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networkscited by 51
  10. 2019Disentangled Representation Learning for 3D Face Shapecited by 48
  11. 20193D Guided Fine-Grained Face Manipulationcited by 45
  12. 2019MVF-Net: Multi-View 3D Face Morphable Model Regressioncited by 45
  13. 2018Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognitioncited by 27
  14. 2021SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstructioncited by 27
  15. 20193D Face Modeling From Diverse Raw Scan Datacited by 25
  16. 2020Survey on 3D face reconstruction from uncalibrated imagescited by 24
  17. 2019Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoderscited by 22
  18. 2017Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognitioncited by 21
  19. 2019Self-supervised Learning of Detailed 3D Face Reconstructioncited by 21
  20. 2016Fitting a 3D Morphable Model to Edges: A Comparison Between Hard and Soft Correspondencescited by 17
  21. 2018Face Synthesis for Eyeglass-Robust Face Recognitioncited by 12
  22. 2019Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Trackingcited by 12
  23. 2018Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalizationcited by 11
  24. 2017Sparse Photometric 3D Face Reconstruction Guided by Morphable Modelscited by 10
  25. 2020Lightweight Photometric Stereo for Facial Details Recoverycited by 8
  26. 2018Head Reconstruction from Internet Photoscited by 5

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Sketch-1-to-3: One Single Sketch to 3D Detailed Face Reconstructioncited by 0