3D shape regression for real-time facial animation

By Chen Cao, Yanlin Weng, Stephen Lin, Kun Zhou. ACM Transactions on Graphics, 2013

379 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9515674638d0c1aa8ac6944efb5b6d23e93b725f

How researchers see this paper

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

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Production-level facial performance capture using deep convolutional neural networks (2016, methodology): “The early work on this area [Cao et al. 2013; Weng et al. 2014] require an actor-specific training step, but later developments have relaxed that requirement [Cao et al. 2014] and also extended the method to smaller-scale features such as wrinkles [Cao et al. 2015; Ichim et al. 2015].”
Towards Fast, Accurate and Stable 3D Dense Face Alignment (2020, background): “, recognition [45,7,26,24,13,51], animation [10], avatar retargeting [9], tracking [50], attribute classification [4,22,21], image restoration [52,12,11], anti-spoofing [49,55,40,54,25].”
Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation (2017, background): “While producing animation movies, tracking the geometry of an actor across multiple frames allows transferring the expression to an animated avatar [14, 8, 7].”
Accurate 3D Face Reconstruction With Weakly-Supervised Learning: From Single Image to Image Set (2019, methodology): “Faithfully recovering the 3D shapes of human faces from unconstrained 2D images is a challenging task and has numerous applications such as face recognition [6, 51, 59], face media manipulation [5, 50], and face animation [10, 23].”
Face2Face: Real-Time Face Capture and Reenactment of RGB Videos (2016, background): “[8] propose a real-time regressionbased approach to infer 3D positions of facial landmarks which constrain a user-specific blendshape model.”
6-DoF object pose from semantic keypoints (2017, background): “, faces [28], cars [29] and human pose [30].”
Face Alignment in Full Pose Range: A 3D Total Solution (2015, background): “, recognition [1], animation [2], tracking [3], attributes classification [4] and image restora-”
Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach (2015, background): “A popular application is human face modeling for various tasks such as recognition [11], feature tracking [12] and facial animation [13].”
Automatic acquisition of high-fidelity facial performances using monocular videos (2014, methodology): “Our multi-linear model is constructed from FaceWarehouse [Cao et al. 2013b], which contains face meshes corresponding to 150 identities and 47 facial expressions.”
High-fidelity Pose and Expression Normalization for face recognition in the wild (2015, methodology): “An alternative method is the landmark based 3D face model fitting [5, 1, 46, 13, 12, 38], which estimates the model parameters with the correspondence between 2D and 3D landmarks.”
DynamicFusion: Reconstruction and tracking of non-rigid scenes in real-time (2015, background): “The best of these demonstrate high accuracy, real-time performance capture for tracking faces [16, 3], hands [21, 20], complete bodies [27], or general articulated objects [23, 33].”
Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors (2018, background): “Precise facial landmark detection lays the foundation for high quality performance of many computer vision and computer graphics tasks, such as face recognition [15], face animation [2] and face reenactment [32].”
Face Alignment at 3000 FPS via Regressing Local Binary Features (2014, methodology): “Our work belongs to the shape regression approach [5, 11, 12, 29, 4, 32, 3] category.”
State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications (2018, methodology): “Online methods target teleconferencing scenarios and focus on driving target rigs (usually non-human avatars) with coarse-scale facial deformation or motion parameters to produce plausible animations [BWP13, CWLZ13, CHZ14, CXH03, LYYB13,SLC11a,WBLP11] (see Fig.”