Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware
Multi-view Geometry Consistency
- URL: http://arxiv.org/abs/2007.12494v1
- Date: Fri, 24 Jul 2020 12:36:09 GMT
- Title: Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware
Multi-view Geometry Consistency
- Authors: Jiaxiang Shang, Tianwei Shen, Shiwei Li, Lei Zhou, Mingmin Zhen, Tian
Fang, Long Quan
- Abstract summary: We propose a self-supervised training architecture by leveraging the multi-view geometry consistency.
We design three novel loss functions for multi-view consistency, including the pixel consistency loss, the depth consistency loss, and the facial landmark-based epipolar loss.
Our method is accurate and robust, especially under large variations of expressions, poses, and illumination conditions.
- Score: 40.56510679634943
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent learning-based approaches, in which models are trained by single-view
images have shown promising results for monocular 3D face reconstruction, but
they suffer from the ill-posed face pose and depth ambiguity issue. In contrast
to previous works that only enforce 2D feature constraints, we propose a
self-supervised training architecture by leveraging the multi-view geometry
consistency, which provides reliable constraints on face pose and depth
estimation. We first propose an occlusion-aware view synthesis method to apply
multi-view geometry consistency to self-supervised learning. Then we design
three novel loss functions for multi-view consistency, including the pixel
consistency loss, the depth consistency loss, and the facial landmark-based
epipolar loss. Our method is accurate and robust, especially under large
variations of expressions, poses, and illumination conditions. Comprehensive
experiments on the face alignment and 3D face reconstruction benchmarks have
demonstrated superiority over state-of-the-art methods. Our code and model are
released in https://github.com/jiaxiangshang/MGCNet.
Related papers
- 3D Face Reconstruction With Geometry Details From a Single Color Image Under Occluded Scenes [4.542616945567623]
3D face reconstruction technology aims to generate a face stereo model naturally and realistically.
Previous deep face reconstruction approaches are typically designed to generate convincing textures.
By introducing bump mapping, we successfully added mid-level details to coarse 3D faces.
arXiv Detail & Related papers (2024-12-25T15:16:02Z) - Generative Face Parsing Map Guided 3D Face Reconstruction Under Occluded Scenes [4.542616945567623]
A complete face parsing map generation method guided by landmarks is proposed.
An excellent anti-occlusion face reconstruction method should ensure the authenticity of the output.
arXiv Detail & Related papers (2024-12-25T14:49:41Z) - G-NeRF: Geometry-enhanced Novel View Synthesis from Single-View Images [45.66479596827045]
We propose a Geometry-enhanced NeRF (G-NeRF), which seeks to enhance the geometry priors by a geometry-guided multi-view synthesis approach.
To tackle the absence of multi-view supervision for single-view images, we design the depth-aware training approach.
arXiv Detail & Related papers (2024-04-11T04:58:18Z) - FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models [67.96827539201071]
We propose a novel test-time optimization approach for 3D scene reconstruction.
Our method achieves state-of-the-art cross-dataset reconstruction on five zero-shot testing datasets.
arXiv Detail & Related papers (2023-08-10T17:55:02Z) - Single-view 3D Mesh Reconstruction for Seen and Unseen Categories [69.29406107513621]
Single-view 3D Mesh Reconstruction is a fundamental computer vision task that aims at recovering 3D shapes from single-view RGB images.
This paper tackles Single-view 3D Mesh Reconstruction, to study the model generalization on unseen categories.
We propose an end-to-end two-stage network, GenMesh, to break the category boundaries in reconstruction.
arXiv Detail & Related papers (2022-08-04T14:13:35Z) - Implicit Neural Deformation for Multi-View Face Reconstruction [43.88676778013593]
We present a new method for 3D face reconstruction from multi-view RGB images.
Unlike previous methods which are built upon 3D morphable models, our method leverages an implicit representation to encode rich geometric features.
Our experimental results on several benchmark datasets demonstrate that our approach outperforms alternative baselines and achieves superior face reconstruction results compared to state-of-the-art methods.
arXiv Detail & Related papers (2021-12-05T07:02:53Z) - Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo
Collection [65.92058628082322]
Non-parametric face modeling aims to reconstruct 3D face only from images without shape assumptions.
This paper presents a novel Learning to Aggregate and Personalize framework for unsupervised robust 3D face modeling.
arXiv Detail & Related papers (2021-06-15T03:10:17Z) - Learning 3D Face Reconstruction with a Pose Guidance Network [49.13404714366933]
We present a self-supervised learning approach to learning monocular 3D face reconstruction with a pose guidance network (PGN)
First, we unveil the bottleneck of pose estimation in prior parametric 3D face learning methods, and propose to utilize 3D face landmarks for estimating pose parameters.
With our specially designed PGN, our model can learn from both faces with fully labeled 3D landmarks and unlimited unlabeled in-the-wild face images.
arXiv Detail & Related papers (2020-10-09T06:11:17Z) - Learning Complete 3D Morphable Face Models from Images and Videos [88.34033810328201]
We present the first approach to learn complete 3D models of face identity geometry, albedo and expression just from images and videos.
We show that our learned models better generalize and lead to higher quality image-based reconstructions than existing approaches.
arXiv Detail & Related papers (2020-10-04T20:51:23Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.