FAGhead: Fully Animate Gaussian Head from Monocular Videos
Not on the map. Why?
Abstract (arXiv)
High-fidelity reconstruction of 3D human avatars has a wild application in visual reality. In this paper, we introduce FAGhead, a method that enables fully controllable human portraits from monocular videos. We explicit the traditional 3D morphable meshes (3DMM) and optimize the neutral 3D Gaussians to reconstruct with complex expressions. Furthermore, we employ a novel Point-based Learnable Representation Field (PLRF) with learnable Gaussian point positions to enhance reconstruction performance. Meanwhile, to effectively manage the edges of avatars, we introduced the alpha rendering to supervise the alpha value of each pixel. Extensive experimental results on the open-source datasets and our capturing datasets demonstrate that our approach is able to generate high-fidelity 3D head avatars and fully control the expression and pose of the virtual avatars, which is outperforming than existing works.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 41 of its 63 references that are in the map. First posted on arXiv 27 Jun 2024.
Builds on
41 of 63 references.
References · 41
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
- 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
- 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
- 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
- 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
- 2020Neural Sparse Voxel Fieldscited by 959
- 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
29 more
- 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
- 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
- 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
- 2021Advances in Neural Renderingcited by 365
- 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
- 2018Deep Video Portraitscited by 267
- 2023GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussianscited by 260
- 2022EMOCA: Emotion Driven Monocular Face Capture and Animationcited by 255
- 2019Neural Voice Puppetry: Audio-driven Facial Reenactmentcited by 250
- 2021Neural Head Avatars from Monocular RGB Videoscited by 213
- 2023NeRSemble: Multi-view Radiance Field Reconstruction of Human Headscited by 194
- 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 184
- 2023TensoIR: Tensorial Inverse Renderingcited by 168
- 2022Towards Metrical Reconstruction of Human Facescited by 166
- 2022Instant Volumetric Head Avatarscited by 159
- 2018Nonlinear 3D Face Morphable Modelcited by 157
- 2022Reconstructing Personalized Semantic Facial NeRF Models From Monocular Videocited by 128
- 2022RigNeRF: Fully Controllable Neural 3D Portraitscited by 126
- 2019Towards High-fidelity Nonlinear 3D Face Morphable Modelcited by 91
- 2023MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatarcited by 89
- 2019Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Eracited by 87
- 2022AvatarMAV: Fast 3D Head Avatar Reconstruction Using Motion-Aware Neural Voxelscited by 73
- 2023Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesiscited by 72
- 2022ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representationscited by 64
- 2021Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinementcited by 36
- 2023HHAvatar: Gaussian Head Avatar with Dynamic Hairscited by 35
- 2021Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstructioncited by 33
- 2024Rig3DGS: Creating Controllable Portraits from Casual Monocular Videoscited by 16
- 2022Robust Human Matting via Semantic Guidancecited by 12
Built on by
Citing papers per year: 2025: 2.
2 papers.