FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidance
Not on the map. Why?
Abstract (arXiv)
We propose FaceCom, a method for 3D facial shape completion, which delivers high-fidelity results for incomplete facial inputs of arbitrary forms. Unlike end-to-end shape completion methods based on point clouds or voxels, our approach relies on a mesh-based generative network that is easy to optimize, enabling it to handle shape completion for irregular facial scans. We first train a shape generator on a mixed 3D facial dataset containing 2405 identities. Based on the incomplete facial input, we fit complete faces using an optimization approach under image inpainting guidance. The completion results are refined through a post-processing step. FaceCom demonstrates the ability to effectively and naturally complete facial scan data with varying missing regions and degrees of missing areas. Our method can be used in medical prosthetic fabrication and the registration of deficient scanning data. Our experimental results demonstrate that FaceCom achieves exceptional performance in fitting and shape completion tasks. The code is available at https://github.com/dragonylee/FaceCom.git.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 53 references that are in the map. First posted on arXiv 4 Jun 2024.
Builds on
29 of 53 references.
References · 29
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
- 2014Deep Learning Face Attributes in the Wildcited by 3,693
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
- 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
- 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
- 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
- 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
- 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
- 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
- 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 268
17 more
- 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
- 2020FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Predictioncited by 196
- 2022Towards Metrical Reconstruction of Human Facescited by 166
- 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 164
- 2020i3DMM: Deep Implicit 3D Morphable Model of Human Headscited by 109
- 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
- 2019Learning Pyramid-Context Encoder Network for High-Quality Image Inpaintingcited by 94
- 2019Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generationcited by 90
- 2021PD-GAN: Probabilistic Diverse GAN for Image Inpaintingcited by 80
- 2022Learning Neural Parametric Head Modelscited by 73
- 20223D face reconstruction with dense landmarkscited by 70
- 2022ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representationscited by 64
- 2017Deformable Shape Completion with Graph Convolutional Autoencoderscited by 50
- 2019MeshGAN: Non-linear 3D Morphable Models of Facescited by 39
- 2014Multilinear Wavelets: A Statistical Shape Space for Human Facescited by 32
- 2021Voxel-based Network for Shape Completion by Leveraging Edge Generationcited by 32
- 2021Learning Feature Aggregation for Deep 3D Morphable Modelscited by 13
Built on by
Citing papers per year: 2025: 1.
1 paper.