Interactive model‐based reconstruction of the human head using an RGB‐D sensor

Zollhöfer, Michael; Thies, Justus; Colaianni, Matteo; Stamminger, Marc; Greiner, Günther

doi:10.1002/cav.1584

Cited by 13 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…which can be solved using iterative solution techniques like preconditioned conjugate gradient (PCG). Previous works [47], [48] demonstrate the feasibility of this strategy in a GPU optimization framework for dynamics simulation and non-rigid registration, respectively. Combining Eq.…”

Section: Augmented Lagrangian Algorithmmentioning

confidence: 99%

Spatio-Temporal Reconstruction for 3D Motion Recovery

Yang

Guo

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

This paper addresses the challenge of 3D motion recovery by exploiting the spatio-temporal correlations of corrupted 3D skeleton sequences. We propose a new 3D motion recovery method using spatio-temporal reconstruction, which uses joint low-rank and sparse priors to exploit temporal correlation and an isometric constraint for spatial correlation. The proposed model is formulated as a constrained optimization problem, which is efficiently solved by the augmented Lagrangian method with a Gauss-Newton solver for the subproblem of isometric optimization. Experimental results on the CMU motion capture dataset, Edinburgh dataset and two Kinect datasets demonstrate that the proposed approach achieves better motion recovery than state-of-the-art methods. The proposed method is applicable to Kinect-like skeleton tracking devices and pose estimation methods that cannot provide accurate estimation of complex motions, especially in the presence of occlusion.

show abstract

Section: Augmented Lagrangian Algorithmmentioning

confidence: 99%

Spatio-Temporal Reconstruction for 3D Motion Recovery

Yang

Guo

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…Face rig can be created manually by an artist using real photos or 3‐D scans as reference. Generic facial blendshapes can also be generated automatically by tracking the subject's face from an RGB‐D camera or a monocular RGB video . In our system, we utilize facial landmark detection and optical flow tracking to produce blendshapes directly from raw 3‐D facial scans since we seek to use the 3‐D scan data as a primary, rather than adopted, data source.…”

Section: Related Workmentioning

confidence: 99%

Just‐in‐time, viable, 3‐D avatars from scans

Feng

Rosenberg

Shapiro

2017

Computer Animation & Virtual

View full text Add to dashboard Cite

We demonstrate a system that can generate a photorealistic, interactive 3-D character from a human subject that is capable of movement, emotion, speech, and gesture in less than 20 min without the need for 3-D artist intervention or specialized technical knowledge through a near automatic process. Our method uses mostly commodity or off-the-shelf hardware. We demonstrate the just-in-time use of generating such 3-D models for virtual and augmented reality, games, simulation, and communication.We anticipate that the inexpensive generation of such photorealistic models will be useful in many venues where a just-in-time 3-D reconstructions of digital avatars that resemble particular human subjects is necessary.

show abstract

“…Rödel et al [7] introduced a report on shape based analysis of female torsos. We introduce a two-step approach for fitting scan data with a mesh inspired by Zollhöfer et al [8]. They used a statistical model as a prior and introduce additional constraints for an optimization of the result.…”

Section: Related Workmentioning

confidence: 99%

Volume Extraction from Body Scans for Bra Sizing

Colaianni¹,

Siegl²,

Penkunas³

et al. 2015

Proceedings of the 6th International Conference on 3D Body Scanning Technologies, Lugano, Switzerland, 27-28 October 2015

Self Cite

View full text Add to dashboard Cite

We present a novel method for bra sizing based on surface scan data. While the current standard of finding the proper size for brassieres is based on only two 1-dimensional measurements, our approach takes the entire shape information into account. We propose to use the breast's volume as a good approximation for that shape. To compute the breast volume we introduce a robust and automatic algorithm based on measuring the volume difference of a torso with and without the breasts. Finally, we compare our novel sizing strategy to the traditional sizing of bras. We will show a better distribution across the population of test-subjects. Using the surface scan data in combination with our volume based sizing approach we can furthermore generate mean body shapes for every bra size which is of great benefit for bra development.

show abstract

Interactive model‐based reconstruction of the human head using an RGB‐D sensor

Cited by 13 publications

References 35 publications

Spatio-Temporal Reconstruction for 3D Motion Recovery

Spatio-Temporal Reconstruction for 3D Motion Recovery

Just‐in‐time, viable, 3‐D avatars from scans

Volume Extraction from Body Scans for Bra Sizing

Contact Info

Product

Resources

About