Ieee Transactions on Pattern Analysis and Machine Intelligence 1 3d Face Reconstruction from a Single Image Using a Single Reference Face Shape

By Ira Kemelmacher-Shlizerman, Ronen Basri

How researchers see this paper

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

Citations in the corpus

MarrNet: 3D Shape Reconstruction via 2.5D Sketches (2017, background): “In the field of computer vision, there have also been abundant works exploiting the idea for reconstruction 3D shapes of faces [Kemelmacher-Shlizerman and Basri, 2011], objects [Tappen et al.”
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (2016, background): “The shape priors are typically encoded in the form of simple 3D primitives as demonstrated by early pioneering works [19,20] or learned from rich repositories of 3D CAD models [21,22,23], whereby the concept of ﬁtting 3D models to images of faces was explored to a much larger extent [24,25,26].”
Internet Based Morphable Model (2013, methodology): “Note that [19] is not designed to work with facial expressions and its performance degrades when the input photo is less similar to the reference template thus we show results on adults with neutral expression.”
Extreme 3D Face Reconstruction: Looking Past Occlusions (2017, methodology): “The ﬁrst goal, exempliﬁed by early 3D morphable models (3DMM) [2, 5, 33], some later shape from shading (SfS) techniques [25, 27], and several recent deep learning methods [36, 39], is obtaining highly detailed 3D face shapes.”
Automatic acquisition of high-fidelity facial performances using monocular videos (2014, methodology): “Our work on fine-scale detail reconstruction builds on the success of modeling fine-scale facial geometry from a single image proposed by [Kemelmacher-Shlizerman and Basri 2011].”
SfSNet: Learning Shape, Reflectance and Illuminance of Faces 'in the Wild' (2017, methodology): “SfS, where a 3DMM or a reference shape is first fitted and then used as a prior to recover the details [13, 14].”
Static and dynamic 3D facial expression recognition: A comprehensive survey (2012, background): “Automatic 3D face reconstruction from a single facial image of low resolution is an emerging research topic in computer vision [8,9].”
Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (2018, background): “[36,37,38,17,39] can produce a 3D structure by warping the shape of a reference 3D model.”
Total Moving Face Reconstruction (2014, methodology): “2, we pre-compute I (P(v′)) and further linearize by precomputing the normalizing factor ‖(wu − w) × (wv − w)‖ as suggested in [30] using the deformed mesh.”
Extreme 3D Face Reconstruction: Seeing Through Occlusions (2017, background): “and often detailed reconstructions [26, 29].”
Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression (2017, methodology): “Given training data like the one produced by [10, 23], then we believe that our method has the capacity to learn finer facial details, too.”
Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation (2017, methodology): “Indeed, for many facial reconstruction tasks providing only the depth profile is sufficient [18, 26].”