Data to 7 Oct 2026

Towards Fast, Accurate and Stable 3D Dense Face Alignment

arXiv 2009.09960 ↗First posted 21 Sep 2020cs.CVcited by 219

Not on the map. Why?

Abstract (arXiv)

Existing methods of 3D dense face alignment mainly concentrate on accuracy, thus limiting the scope of their practical applications. In this paper, we propose a novel regression framework named 3DDFA-V2 which makes a balance among speed, accuracy and stability. Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously. To further improve the stability on videos, we present a virtual synthesis method to transform one still image to a short-video which incorporates in-plane and out-of-plane face moving. On the premise of high accuracy and stability, 3DDFA-V2 runs at over 50fps on a single CPU core and outperforms other state-of-the-art heavy models simultaneously. Experiments on several challenging datasets validate the efficiency of our method. Pre-trained models and code are available at https://github.com/cleardusk/3DDFA_V2.

Key facts. Cited by 219 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 39; 2022: 40; 2023: 45; 2024: 53; 2025: 26; 2026: 16.

219 papers.

Sort:

By area:

2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 254
2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
2022Towards Metrical Reconstruction of Human Facescited by 165
2022EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Modelcited by 151
2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
2022RigNeRF: Fully Controllable Neural 3D Portraitscited by 126
2022Realistic One-shot Mesh-based Head Avatarscited by 119
2024WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wildcited by 117
2022FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Datasetcited by 98
2021MoFaNeRF: Morphable Facial Neural Radiance Fieldcited by 94
2023PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360circcited by 93
2021Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmarkcited by 82

38 more

2024SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesiscited by 81
20223D face reconstruction with dense landmarkscited by 70
2021OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wildcited by 50
2022Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videoscited by 50
2022SPACE: Speech-driven Portrait Animation with Controllable Expressioncited by 49
2023GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variationscited by 49
2021Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracingcited by 48
2021Dual-Cross Central Difference Network for Face Anti-Spoofingcited by 47
2022Emotion-Controllable Generalized Talking Face Generationcited by 43
2022FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstructioncited by 39
2022FDNeRF: Few-shot Dynamic Neural Radiance Fields for Face Reconstruction and Expression Editingcited by 38
20233D Face Reconstruction with the Geometric Guidance of Facial Part Segmentationcited by 38
2021FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstructioncited by 34
2022Geometry-aware Single-image Full-body Human Relightingcited by 34
2021FLAME-in-NeRF : Neural control of Radiance Fields for Free View Face Animationcited by 33
2021Video Transformer for Deepfake Detection with Incremental Learningcited by 33
2022REALY: Rethinking the Evaluation of 3D Face Reconstructioncited by 32
2023High-Fidelity 3D Face Generation from Natural Language Descriptionscited by 32
2022DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Imagecited by 31
2024FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Videocited by 31
2023MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentionscited by 29
2022Temporally Consistent Semantic Video Editingcited by 28
2021SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstructioncited by 27
2021Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometrycited by 27
2022JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstructioncited by 26
2021SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfercited by 22
2023HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Detailscited by 22
2023Controllable Inversion of Black-Box Face Recognition Models via Diffusioncited by 22
2021Robust Model-based Face Reconstruction through Weakly-Supervised Outlier Segmentationcited by 20
20243D Face Tracking from 2D Video through Iterative Dense UV to Image Flowcited by 20
2025Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstructioncited by 20
2022Talking Face Generation with Multilingual TTScited by 18
2022Video-driven Neural Physically-based Facial Asset for Productioncited by 17
2022S2F2: Self-Supervised High Fidelity Face Reconstruction from Monocular Imagecited by 17
2021Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collectioncited by 16
2022Neural Parameterization for Dynamic Human Head Editingcited by 16
2022Prepended Domain Transformer: Heterogeneous Face Recognition without Bells and Whistlescited by 16
2024Rig3DGS: Creating Controllable Portraits from Casual Monocular Videoscited by 16

50 most cited of 219 All 219 (JSON)