mlsanityData to 14 Oct 2026

3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation

arXiv 2312.00311 ↗First posted 1 Dec 2023cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

3D Morphable Models (3DMMs) provide promising 3D face reconstructions in various applications. However, existing methods struggle to reconstruct faces with extreme expressions due to deficiencies in supervisory signals, such as sparse or inaccurate landmarks. Segmentation information contains effective geometric contexts for face reconstruction. Certain attempts intuitively depend on differentiable renderers to compare the rendered silhouettes of reconstruction with segmentation, which is prone to issues like local optima and gradient instability. In this paper, we fully utilize the facial part segmentation geometry by introducing Part Re-projection Distance Loss (PRDL). Specifically, PRDL transforms facial part segmentation into 2D points and re-projects the reconstruction onto the image plane. Subsequently, by introducing grid anchors and computing different statistical distances from these anchors to the point sets, PRDL establishes geometry descriptors to optimize the distribution of the point sets for face reconstruction. PRDL exhibits a clear gradient compared to the renderer-based methods and presents state-of-the-art reconstruction performance in extensive quantitative and qualitative experiments. Our project is available at https://github.com/wang-zidu/3DDFA-V3 .

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 34 of its 65 references that are in the map. First posted on arXiv 1 Dec 2023.

Builds on

34 of 65 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  5. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 628
  6. 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 482
  7. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
  8. 2017Neural 3D Mesh Renderercited by 437
  9. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  10. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  11. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  12. 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
22 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. 2022Towards Metrical Reconstruction of Human Facescited by 166
  4. 2016Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registrationcited by 159
  5. 2018Face Alignment in Full Pose Range: A 3D Total Solutioncited by 148
  6. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 112
  7. 2018Unsupervised Training for 3D Morphable Model Regressioncited by 100
  8. 2019Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Researchcited by 98
  9. 2022FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Datasetcited by 98
  10. 2020Learning Formation of Physically-Based Face Attributescited by 94
  11. 2020Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistencycited by 78
  12. 2019Real-time Facial Surface Geometry from Monocular Video on Mobile GPUscited by 73
  13. 2023A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Imagescited by 43
  14. 2020Learning Complete 3D Morphable Face Models from Images and Videoscited by 35
  15. 2019Face Parsing with RoI Tanh-Warpingcited by 33
  16. 2022REALY: Rethinking the Evaluation of 3D Face Reconstructioncited by 33
  17. 2022DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Imagecited by 31
  18. 2022Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsingcited by 26
  19. 2021RoI Tanh-polar Transformer Network for Face Parsing in the Wildcited by 23
  20. 2022Towards 3D Face Reconstruction in Perspective Projection: Estimating 6DoF Face Pose from Monocular Imagecited by 9
  21. 2022Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shapecited by 5
  22. 2022Mesh-Tension Driven Expression-Based Wrinkles for Synthetic Facescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 17; 2026: 18.

38 papers.

Sort:

By area:

  1. 2025TEASER: Token Enhanced Spatial Modeling for Expressions Reconstructioncited by 14
  2. 2024RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Imagescited by 10
  3. 2025DynamicFace: High-Quality and Consistent Face Swapping for Image and Video using Composable 3D Facial Priorscited by 10
  4. 2025DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learningcited by 10
  5. 2026DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformercited by 9
  6. 2025FreeUV: Ground-Truth-Free Realistic Facial UV Texture Recovery via Cross-Assembly Inference Strategycited by 7
  7. 2025PC-Talk: Precise Facial Animation Control for Audio-Driven Talking Face Generationcited by 6
  8. 2024S2TD-Face: Reconstruct a Detailed 3D Face with Controllable Texture from a Single Sketchcited by 5
  9. 2024SEREP: Semantic Facial Expression Representation for Robust In-the-Wild Capture and Retargetingcited by 4
  10. 2025STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstructioncited by 4
  11. 2025VGGTFace: Topologically Consistent Facial Geometry Reconstruction in the Wildcited by 4
  12. 2025SRM-Hair: Single Image Head Mesh Reconstruction via 3D Morphable Haircited by 2
26 more
  1. 2025High-Quality Facial Albedo Generation for 3D Face Reconstruction from a Single Image using a Coarse-to-Fine Approachcited by 2
  2. 2025Driver-Net: Multi-Camera Fusion for Assessing Driver Take-Over Readiness in Automated Vehiclescited by 2
  3. 2025BFSM: 3D Bidirectional Face-Skull Morphable Modelcited by 2
  4. 2025AvatarTex: High-Fidelity Facial Texture Reconstruction from Single-Image Stylized Avatarscited by 1
  5. 2026MANGO:Natural Multi-speaker 3D Talking Head Generation via 2D-Lifted Enhancementcited by 1
  6. 2026Skullptor: High Fidelity 3D Head Reconstruction in Seconds with Multi-View Normal Predictioncited by 1
  7. 2026Any3DAvatar: Fast and High-Quality Full-Head 3D Avatar Reconstruction from Single Portrait Imagecited by 1
  8. 2026Monocular Avatar Reconstruction via Cascaded Diffusion Priors and UV-Space Differentiable Shadingcited by 1
  9. 2025High-Quality 3D Head Reconstruction from Any Single Portrait Imagecited by 0
  10. 2025Improving Facial Rig Semantics for Tracking and Retargetingcited by 0
  11. 2025Hierarchical MLANet: Multi-level Attention for 3D Face Reconstruction From Single Imagescited by 0
  12. 2025MSMA: Multi-Scale Feature Fusion For Multi-Attribute 3D Face Reconstruction From Unconstrained Imagescited by 0
  13. 2025GLVD: Guided Learned Vertex Descentcited by 0
  14. 2026Exploring Specular Reflection Inconsistency for Generalizable Face Forgery Detectioncited by 0
  15. 2026Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Featurescited by 0
  16. 2026Profile-Specific 3DMM Regression from a Single Lateral Face Imagecited by 0
  17. 2026FaceParts: Segmentation and Editing of Gaussian Splattingcited by 0
  18. 2026OMGTex: One-stage Multi-style Facial Texture Reconstruction without Geometry Guidancecited by 0
  19. 2026ArtBoost: Synthetic Articulatory Data Augmentation for Acoustic-to-Articulatory Inversioncited by 0
  20. 2026CUPID: Reconstructing UV Texture Maps for Interpretable Person-of-Interest Deepfake Detectioncited by 0
  21. 2026TIGER: Taming Identity, Geometry, and Generative Priors for High-Quality Face Video Restorationcited by 0
  22. 2026Discovering Geometric Biases in 3D Face Reconstruction: A Curvature-Aware Spectral Framework for Fairness Evaluationcited by 0
  23. 2026UVFaceFusion: Fast Multi-view Topologically Consistent Face Reconstruction in the Wild via UV-space Neural Fusioncited by 0
  24. 2026GRAPE: Graduated Routing for Articulated Portrait mesh Estimationcited by 0
  25. 2026FaceSnap: Real-Time Personalized Lightstage Facial Performance Capturecited by 0
  26. 2026Relightable 3D Avatar Reconstruction with Semantic-Adaptive Motion-Illumination Responsescited by 0