mlsanityData to 7 Oct 2026

A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimization

arXiv 2310.03205 ↗First posted 4 Oct 2023cs.CV cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

We propose NeuFace, a 3D face mesh pseudo annotation method on videos via neural re-parameterized optimization. Despite the huge progress in 3D face reconstruction methods, generating reliable 3D face labels for in-the-wild dynamic videos remains challenging. Using NeuFace optimization, we annotate the per-view/-frame accurate and consistent face meshes on large-scale face videos, called the NeuFace-dataset. We investigate how neural re-parameterization helps to reconstruct image-aligned facial details on 3D meshes via gradient analysis. By exploiting the naturalness and diversity of 3D faces in our dataset, we demonstrate the usefulness of our dataset for 3D face-related tasks: improving the reconstruction accuracy of an existing 3D face reconstruction model and learning 3D facial motion prior. Code and datasets will be available at https://neuface-dataset.github.io.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 62 of its 95 references that are in the map. First posted on arXiv 4 Oct 2023.

Builds on

62 of 95 references.

References · 62

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  4. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  5. 2019HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clipscited by 946
  6. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  7. 2018VoxCeleb2: Deep Speaker Recognitioncited by 862
  8. 2018A Convergence Theory for Deep Learning via Over-Parameterizationcited by 784
  9. 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
  10. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  11. 2018Gradient Descent Provably Optimizes Over-parameterized Neural Networkscited by 655
  12. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
38 more
  1. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  2. 2018Gradient Descent Finds Global Minima of Deep Neural Networkscited by 572
  3. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
  4. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 475
  5. 2020One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencingcited by 438
  6. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  7. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  8. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 294
  9. 20193D Morphable Face Models -- Past, Present and Futurecited by 269
  10. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
  11. 2018Deep Video Portraitscited by 265
  12. 2021Mesh Graphormercited by 264
  13. 2019Capture, Learning, and Synthesis of 3D Speaking Stylescited by 257
  14. 2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 254
  15. 2022CelebV-HQ: A Large-Scale Video Facial Attributes Datasetcited by 246
  16. 2018Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodiescited by 239
  17. 2020Towards Fast, Accurate and Stable 3D Dense Face Alignmentcited by 219
  18. 2021Neural Head Avatars from Monocular RGB Videoscited by 212
  19. 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
  20. 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
  21. 2021MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglementcited by 189
  22. 2019Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervisioncited by 176
  23. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  24. 2022Towards Metrical Reconstruction of Human Facescited by 165
  25. 2020Monocular Expressive Body Regression through Body-Driven Attentioncited by 155
  26. 2019GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstructioncited by 150
  27. 2018Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networkscited by 140
  28. 2021Pixel Codec Avatarscited by 125
  29. 2022Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motioncited by 125
  30. 2022Realistic One-shot Mesh-based Head Avatarscited by 119
  31. 2018FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Facescited by 118
  32. 2016Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Networkcited by 109
  33. 2020ID-Reveal: Identity-aware DeepFake Video Detectioncited by 97
  34. 2022DigiFace-1M: 1 Million Digital Face Images for Face Recognitioncited by 92
  35. 2021On Self-Contact and Human Posecited by 88
  36. 2022Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformerscited by 81
  37. 2022Learning Audio-Video Modalities from Image Captionscited by 80
  38. 2020Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistencycited by 78

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 1; 2026: 1.

5 papers.

  1. 2023Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Renderingcited by 84
  2. 2023LaughTalk: Expressive 3D Talking Head Generation with Laughtercited by 27
  3. 2025How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objectscited by 5
  4. 2023Anatomically Constrained Implicit Face Modelscited by 4
  5. 2026FiCA: Feed-forward instant Gaussian Codec Avatars from a Single Portrait Imagecited by 0