3D Face Hallucination from a Single Depth Frame

Liang, Shu; Kemelmacher-Shlizerman, Ira; Shapiro, Linda G.

doi:10.1109/3dv.2014.67

Cited by 14 publications

(10 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many approaches use an RGBD sensor to reconstruct face models [Cao et al 2014b;Liang et al 2014] and/or to animate them based on captured performance data [Bouaziz et al 2013;Hsieh et al 2015;Thies et al 2015]. However, their face reconstructions suffer from low quality in geometry and texture, due to the inherent limitations of current RGBD sensors.…”

Section: Face Reconstructionmentioning

confidence: 99%

Fast generation of realistic virtual humans

Achenbach

Waltemate

Latoschik

et al. 2017

Proceedings of the 23rd ACM Symposium on Virtual Reality Software and Technology

View full text Add to dashboard Cite

Figure 1: We generate realistic virtual humans from real persons through multi-view stereo scanning. The resulting characters are ready to be animated through a skeletal rig and facial blendshapes, and are compatible with standard graphics and VR engines. The whole reconstruction process requires only minimal user input and takes less than ten minutes. ABSTRACTIn this paper we present a complete pipeline to create ready-toanimate virtual humans by fitting a template character to a point set obtained by scanning a real person using multi-view stereo reconstruction. Our virtual humans are built upon a holistic character model and feature a detailed skeleton, fingers, eyes, teeth, and a rich set of facial blendshapes. Furthermore, due to the careful selection of techniques and technology, our reconstructed humans are quite realistic in terms of both geometry and texture. Since we represent our models as single-layer triangle meshes and animate them through standard skeleton-based skinning and facial blendshapes, our characters can be used in standard VR engines out of the box. By optimizing for computation time and minimizing manual intervention, our reconstruction pipeline is capable of processing whole characters in less than ten minutes.

show abstract

Section: Face Reconstructionmentioning

confidence: 99%

Fast generation of realistic virtual humans

Achenbach

Waltemate

Latoschik

et al. 2017

Proceedings of the 23rd ACM Symposium on Virtual Reality Software and Technology

View full text Add to dashboard Cite

show abstract

“…Since all the face shapes in the 3D face dataset are in dense correspondence, we transfer these 66 landmarks to all the output 3D faces. We then deform the generic shape towards the 3D face shape using the landmarks, following [Liang et al 2014]. We fuse the deformed generic head shape and the face shape using Poisson surface reconstruction [Kazhdan and Hoppe 2013] and get a complete head shape.…”

Section: Face Modelmentioning

confidence: 99%

Video to fully automatic 3D hair model

et al. 2018

Self Cite

View full text Add to dashboard Cite

views, since taking your −90 ∘ , 90 ∘ , and full back views is not feasible in a selfie capture.In the core of our system, in addition to the automatization components, hair strands are estimated and deformed in 3D (rather than 2D as in state of the art) thus enabling superior results. We provide qualitative, quantitative, and Mechanical Turk human studies that support the proposed system, and show results on a diverse variety of videos (8 different celebrity videos, 9 selfie mobile videos, spanning age, gender, hair length, type, and styling).

show abstract

“…Other approaches [Garrido et al 2016] reconstruct personalized face rigs, including reflectance and fine-scale detail from monocular video. Liang et al [Liang et al 2014] reconstruct the identity of a face from monocular Kinect data using a part-based matching algorithm. They select face parts (eyes,nose,mouth,cheeks) from a database of faces that best match the input data.…”

Section: Related Workmentioning

confidence: 99%

Headon

et al. 2018

View full text Add to dashboard Cite

Fig. 1. Our novel HeadOn approach enables real-time reenactment of upper body motion, head pose, face expression, and eye gaze in human portrait videos. For synthesis of new photo-realistic video content, we employ a novel video-based rendering approach that builds on top of a fully controllable 3D actor model. The person-specific model is constructed from a short RGB-D calibration sequence and is driven by a real-time torso and face tracker.We propose HeadOn, the first real-time source-to-target reenactment approach for complete human portrait videos that enables transfer of torso and head motion, face expression, and eye gaze. Given a short RGB-D video of the target actor, we automatically construct a personalized geometry proxy that embeds a parametric head, eye, and kinematic torso model. A novel realtime reenactment algorithm employs this proxy to photo-realistically map the captured motion from the source actor to the target actor. On top of the coarse geometric proxy, we propose a video-based rendering technique that composites the modified target portrait video via view-and pose-dependent texturing, and creates photo-realistic imagery of the target actor under novel torso and head poses, facial expressions, and gaze directions. To this end, we propose a robust tracking of the face and torso of the source actor. We extensively evaluate our approach and show significant improvements in enabling much greater flexibility in creating realistic reenacted output videos.

show abstract

3D Face Hallucination from a Single Depth Frame

Cited by 14 publications

References 42 publications

Fast generation of realistic virtual humans

Fast generation of realistic virtual humans

Video to fully automatic 3D hair model

Headon

Contact Info

Product

Resources

About