dongpoli/face-3d-study

Face 3D Reconstruction papers or codes

Face-3D-Study 论文代码

有关3D人脸重建的论文和代码，做个记录，以便与学习，和后来者阅读；黑桃符号(♠):表示 我已读过。

2020 论文代码

2020 CVPR

• FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction [] (百度)
• Towards High-Fidelity 3D Face Reconstruction From In-the-Wild Images Using Graph Convolutional Networks
• ReDA:Reinforced Differentiable Attribute for 3D Face Reconstruction
• AvatarMe: Realistically Renderable 3D Facial Reconstruction "In-the-Wild"
• Uncertainty-Aware Mesh Decoder for High Fidelity 3D Face Reconstruction
• Deep Facial Non-Rigid Multi-View Stereo

2019 论文代码

• Face Reconstruction from Voice using Generative dversarial Networks [paper]
• 3D Dense Face Alignment via Graph Convolution Networks [paper] （♠）
• 2DASL: Joint 3D Face Reconstruction and Dense Face Alignment from A Single Image with 2D-Assisted Self-Supervised Learning [paper]. [code] （♠）
• On learning 3d face morphable model from in-the-wild images [paper] (TPAMI)

2019 CVPR

• GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction [paper]. [code]
• Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision [paper]
• Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoders [paper]
• MMFace: A Multi-Metric Regression Network for Unconstrained Face Reconstruction[paper].
• Towards High-Fidelity Nonlinear 3D Face Morphable Model [paper]. [code].[project]
• MVF-Net: Multi-View 3D Face Morphable Model Regression [paper]. [code] （♠）(多视图重建)
• RingNet: Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision [paper].[code]. [project]
• Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking [paper]. （♠）
• Speech2Face: Learning the Face Behind a Voice [paper]

ICCV

• 3D Face Shape Regression From 2D Videos with Multi-reconstruction and Mesh Retrieval [paper] (3DFAW比赛论文)
• The 2 nd 3D Face Alignment in the Wild Challenge (3DFAW-Video): Dense Reconstruction From Video[paper] (3DFAW比赛论文， 从Video重建3D人脸 研究趋势)
• DF2Net: A Dense-Fine-Finer Network for Detailed 3D Face Reconstruction [paper]

2018 论文代码

• State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications [paper] (人脸重建综述)
• Deep Appearance Models for Face Rendering [paper]
• Multilinear Autoencoder for 3D Face Model Learning [paper]

2018 CVPR

• Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition [paper] (♠)
• Unsupervised Training for 3D Morphable Model Regression [paper]
• Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz [paper]
• Nonlinear 3D Face Morphable Model [paper]

2018 ECCV

• Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network [paper]. [code] (PRNet) （♠）
• Generating 3D faces using Convolutional Mesh Autoencoders [paper]
• Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition [paper]

2017 论文代码

2017 CVPR

• DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild [paper]
• Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network [paper]. [code]. [project] (3dmm_cnn) (♠)
• Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression [paper] [code] (VRN)
• Reconstruction-Based Disentanglement for Pose-invariant Face Recognition [paper]
• End-to-end 3D face reconstruction with deep neural networks [paper] (♠)
• Learning Detailed Face Reconstruction from a Single Image [paper]
• Photorealistic Facial Texture Inference Using Deep Neural Networks [paper] (纹理方面)

2017 ICCV

• Dense Face Alignment [paper]
• How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks) [paper]
• Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation [paper]
• MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction [paper]

2016 论文代码

• 3D Face Reconstruction by Learning from Synthetic Data [paper]

2016 CVPR

• Face Alignment Across Large Poses: A 3D Solution [paper]. [code] （♠）
• Face Alignment in Full Pose Range: A 3D Total Solution [paper]. [code]. [project] [不是CVPR 是TPAMI / PAMI] [3DDFA]