All Outputs (5)

Photo-Realistic Facial Details Synthesis from Single Image (2019)
Presentation / Conference Contribution
Chen, A., Chen, Z., Zhang, G., Zhang, Z., Mitchell, K., & Yu, J. (2019, October). Photo-Realistic Facial Details Synthesis from Single Image. Presented at 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea

We present a single-image 3D face synthesis technique that can handle challenging facial expressions while recovering fine geometric details. Our technique employs expression analysis for proxy face geometry generation and combines supervised and uns... Read More about Photo-Realistic Facial Details Synthesis from Single Image.

Recycling a Landmark Dataset for Real-time Facial Capture and Animation with Low Cost HMD Integrated Cameras (2019)
Presentation / Conference Contribution
Dos Santos Brito, C. J., & Mitchell, K. (2019, November). Recycling a Landmark Dataset for Real-time Facial Capture and Animation with Low Cost HMD Integrated Cameras. Presented at VRCAI ’19, Brisbane, QLD, Australia

Preparing datasets for use in the training of real-time face tracking algorithms for HMDs is costly. Manually annotated facial landmarks are accessible for regular photography datasets, but introspectively mounted cameras for VR face tracking have in... Read More about Recycling a Landmark Dataset for Real-time Facial Capture and Animation with Low Cost HMD Integrated Cameras.

JUNGLE: An Interactive Visual Platform for Collaborative Creation and Consumption of Nonlinear Transmedia Stories (2019)
Presentation / Conference Contribution
Kapadia, M., Muniz, C. M., Sohn, S. S., Pan, Y., Schriber, S., Mitchell, K., & Gross, M. (2019, November). JUNGLE: An Interactive Visual Platform for Collaborative Creation and Consumption of Nonlinear Transmedia Stories. Presented at International Conference on Interactive Digital Storytelling (ICIDS 2019), Salt Lake City, Utah, USA

JUNGLE is an interactive, visual platform for the collaborative manipulation and consumption of nonlinear transmedia stories. Intuitive visual interfaces encourage JUNGLE users to explore vast libraries of story worlds, expand existing stories, or co... Read More about JUNGLE: An Interactive Visual Platform for Collaborative Creation and Consumption of Nonlinear Transmedia Stories.

Light Field Synthesis Using Inexpensive Surveillance Camera Systems (2019)
Presentation / Conference Contribution
Dumbgen, F., Schroers, C., & Mitchell, K. (2019). Light Field Synthesis Using Inexpensive Surveillance Camera Systems. . https://doi.org/10.1109/icip.2019.8804269

We present a light field synthesis technique that achieves accurate reconstruction given a low-cost, wide-baseline camera rig. Our system integrates optical flow with methods for rectification, disparity estimation, and feature extraction, which we t... Read More about Light Field Synthesis Using Inexpensive Surveillance Camera Systems.

Deep Precomputed Radiance Transfer for Deformable Objects (2019)
Presentation / Conference Contribution
Li, Y., Wiedemann, P., & Mitchell, K. (2019, May). Deep Precomputed Radiance Transfer for Deformable Objects. Presented at ACM Symposium on Interactive 3D Graphics and Games, Montreal, Quebec, Canada

We propose, DeepPRT, a deep convolutional neural network to compactly encapsulate the radiance transfer of a freely deformable object for rasterization in real-time. With pre-computation of radiance transfer (PRT) we can store complex light interac... Read More about Deep Precomputed Radiance Transfer for Deformable Objects.