InverseFaceNet: Deep Single-Shot Inverse Face Rendering From A Single Image
InverseFaceNet: Deep Single-Shot Inverse Face Rendering From A Single Image
复制标题
DOI：
--
复制
发表时间：
2017-03
期刊：
影响因子：
--
通讯作者：
Hyeongwoo Kim;M. Zollhöfer;A. Tewari;Justus Thies;Christian Richardt;C. Theobalt
中科院分区：
文献类型：
--
作者：
Hyeongwoo Kim;M. Zollhöfer;A. Tewari;Justus Thies;Christian Richardt;C. Theobalt
我们引入了InverseFaceNet，这是一个用于人脸的深度卷积逆渲染框架，它可以在单次拍摄中从单个输入图像中联合估计面部姿势，形状，表情，反射率和照明。通过仅从单个图像估计所有这些参数，单个面部图像上的高级编辑可能性（例如外观编辑和重新照明）变得可行。以前的基于学习的人脸重建方法不能联合恢复所有维度，或者在视觉质量方面受到严重限制。相比之下，我们建议使用深度神经网络来恢复高质量的面部姿势，形状，表情，反射率和照明，该深度神经网络使用大型综合创建的数据集进行训练。我们的方法建立在一个新的损失函数，直接在参数空间中测量模型空间的相似性，并显着提高重建精度。此外，我们提出了一种分析合成育种方法，迭代更新的合成训练语料库的基础上分布的真实世界的图像，我们证明了这种策略优于完全综合训练的网络。最后，我们展示了高质量的重建，并将我们的方法与几种最先进的方法进行了比较。
We introduce InverseFaceNet, a deep convolutional inverse rendering framework for faces that jointly estimates facial pose, shape, expression, reflectance and illumination from a single input image in a single shot. By estimating all these parameters from just a single image, advanced editing possibilities on a single face image, such as appearance editing and relighting, become feasible. Previous learning-based face reconstruction approaches do not jointly recover all dimensions, or are severely limited in terms of visual quality. In contrast, we propose to recover high-quality facial pose, shape, expression, reflectance and illumination using a deep neural network that is trained using a large, synthetically created dataset. Our approach builds on a novel loss function that measures model-space similarity directly in parameter space and significantly improves reconstruction accuracy. In addition, we propose an analysis-by-synthesis breeding approach which iteratively updates the synthetic training corpus based on the distribution of real-world images, and we demonstrate that this strategy outperforms completely synthetically trained networks. Finally, we show high-quality reconstructions and compare our approach to several state-of-the-art approaches.