mlsanityData to 14 Oct 2026

GLVD: Guided Learned Vertex Descent

arXiv 2510.06046 ↗First posted 7 Oct 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Existing 3D face modeling methods usually depend on 3D Morphable Models, which inherently constrain the representation capacity to fixed shape priors. Optimization-based approaches offer high-quality reconstructions but tend to be computationally expensive. In this work, we introduce GLVD, a hybrid method for 3D face reconstruction from few-shot images that extends Learned Vertex Descent (LVD) by integrating per-vertex neural field optimization with global structural guidance from dynamically predicted 3D keypoints. By incorporating relative spatial encoding, GLVD iteratively refines mesh vertices without requiring dense 3D supervision. This enables expressive and adaptable geometry reconstruction while maintaining computational efficiency. GLVD achieves state-of-the-art performance in single-view settings and remains highly competitive in multi-view scenarios, all while substantially reducing inference time.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 68 of its 83 references that are in the map. First posted on arXiv 7 Oct 2025.

Builds on

68 of 83 references.

References · 68

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  4. 2018Group Normalizationcited by 1,524
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  6. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  7. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  8. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  9. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  10. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  11. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  12. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
38 more
  1. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
  2. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  3. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 314
  4. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 268
  5. 2023GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussianscited by 260
  6. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  7. 2021I M Avatar: Implicit Morphable Head Avatars from Videoscited by 231
  8. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  9. 2021Neural Head Avatars from Monocular RGB Videoscited by 213
  10. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 184
  11. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  12. 2022Towards Metrical Reconstruction of Human Facescited by 166
  13. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  14. 2022Instant Volumetric Head Avatarscited by 159
  15. 2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 155
  16. 2022PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Imagescited by 153
  17. 2023One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformercited by 130
  18. 2022Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothingcited by 126
  19. 2023GART: Gaussian Articulated Template Modelscited by 121
  20. 2020Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstructioncited by 112
  21. 2016Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Networkcited by 109
  22. 2022FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Datasetcited by 98
  23. 2017Hierarchical Surface Prediction for 3D Object Reconstructioncited by 89
  24. 2020Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wildcited by 82
  25. 2021H3D-Net: Few-Shot High-Fidelity 3D Head Reconstructioncited by 81
  26. 2022KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypointscited by 77
  27. 2016Learning Detailed Face Reconstruction from a Single Imagecited by 71
  28. 2017Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regressioncited by 66
  29. 20163D Face Reconstruction by Learning from Synthetic Datacited by 64
  30. 2022ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representationscited by 64
  31. 2020Portrait Neural Radiance Fields from a Single Imagecited by 61
  32. 2023HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splattingcited by 60
  33. 2021DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Renderingcited by 52
  34. 2020High-Fidelity 3D Digital Human Head Creation from RGB-D Selfiescited by 47
  35. 2019MVF-Net: Multi-View 3D Face Morphable Model Regressioncited by 45
  36. 20233D Human Mesh Estimation from Virtual Markerscited by 44
  37. 2024HeadGAP: Few-Shot 3D Head Avatar via Generalizable Gaussian Priorscited by 44
  38. 2023A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Imagescited by 43

50 most cited of 68 All 68 (JSON)

Built on by

Not cited yet.