Expression flow for 3D-aware face component transfer

By Fei Yang, Jue Wang, Eli Shechtman, Lubomir D. Bourdev, Dimitris N. Metaxas. 2011

170 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Generating 3D faces using Convolutional Mesh Autoencoders (2018, methodology): “[47] use multiple PCA models, one per expression, Amberg et al.”
Editing in Style: Uncovering the Local Semantics of GANs (2020, methodology): “[28] present a method for transferring expression from one face to another.”
Attribute2Image: Conditional Image Generation from Visual Attributes (2015, methodology): “[42] developed an Expression Flow algorithm to transfer the expression from one face image to the other through warping.”
Eye In-painting with Exemplar Generative Adversarial Networks (2017, methodology): “Some examples include red-eye fixing [41] and blemish removal [7], where patch matching and Poisson blending have been used to create plausible-looking results [39].”
Extreme 3D Face Reconstruction: Seeing Through Occlusions (2017, methodology): “Since that seminal work, many improvements were made to the methods used to recover 3DMM face shape parameters [2, 10, 35, 39, 48, 54].”
Effective face frontalization in unconstrained images (2014, background): “Morphable-Models based methods [1, 2, 30, 39] attempt to learn the space of allowable facial geometries us-ing many aligned 3D face models.”
Review of statistical shape spaces for 3D data with comparative analysis for human faces (2012, background): “This approach can be viewed as an extension of morphable models Yang et al. [10] exchanged the expression of a face in a single image based on a different input image of the same subject.”
Extreme 3D Face Reconstruction: Looking Past Occlusions (2017, methodology): “Since that seminal work, many improvements were made to the methods used to recover 3DMM face shape parameters [3, 10, 33, 37, 43, 50].”
Regressing Robust and Discriminative 3D Morphable Models with a Very Deep Neural Network (2016, background): “Statistical shape representations, such as the widely popular 3DMM [5, 6, 11, 28, 32, 40, 45], use many aligned 3D face shapes to learn a distribution of 3D faces, represented as a high dimensional subspace.”
Expressive Body Capture: 3D Hands, Face, and Body From a Single Image (2019, background): “There is also an extensive literature on modelling hands [39, 53, 57, 58, 68, 69, 71, 74, 75] and faces [4, 9, 11, 13, 14, 43, 63, 76, 79] in 3D but in isolation from the rest of the body.”
Neural Face Editing with Intrinsic Image Disentangling (2017, methodology): “We estimate N̂ by fitting coarse face geometry to every image in the training set using a 3D Morphable Model [6].”
Generative Attribute Controller with Conditional Filtered Generative Adversarial Networks (2017, background): “There are two major approaches of attribute-based image editing: example-based [14, 30, 42, 48] and model-based [15, 20].”