All Outputs (9)

Photo-Realistic Facial Details Synthesis from Single Image (2019)
Conference Proceeding
Chen, A., Chen, Z., Zhang, G., Zhang, Z., Mitchell, K., & Yu, J. (2019). Photo-Realistic Facial Details Synthesis from Single Image. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV) (9429-9439). https://doi.org/10.1109/ICCV.2019.00952

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)
Conference Proceeding
Dos Santos Brito, C. J., & Mitchell, K. (2019). Recycling a Landmark Dataset for Real-time Facial Capture and Animation with Low Cost HMD Integrated Cameras. In VRCAI '19: The 17th International Conference on Virtual-Reality Continuum and its Applications in Industry. https://doi.org/10.1145/3359997.3365690

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)
Conference Proceeding
Kapadia, M., Muniz, C. M., Sohn, S. S., Pan, Y., Schriber, S., Mitchell, K., & Gross, M. (2019). JUNGLE: An Interactive Visual Platform for Collaborative Creation and Consumption of Nonlinear Transmedia Stories. In Interactive Storytelling: 12th International Conference on Interactive Digital Storytelling, ICIDS 2019, Little Cottonwood Canyon, UT, USA, November 19–22, 2019, Proceedings (250-266). https://doi.org/10.1007/978-3-030-33894-7_26

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.

Depth codec for real-time, high-quality light field reconstruction (2019)
Patent
Mitchell, K., Koniaris, C., Kosek, M., & Sinclair, D. Depth codec for real-time, high-quality light field reconstruction. US20190313080A1

Systems, methods, and articles of manufacture are disclosed that enable the compression of depth data and real-time reconstruction of high-quality light fields. In one aspect, spatial compression and decompression of depth images is divided into the... Read More about Depth codec for real-time, high-quality light field reconstruction.

Light Field Synthesis Using Inexpensive Surveillance Camera Systems (2019)
Conference Proceeding
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.

Intermediated Reality: A Framework for Communication Through Tele-Puppetry (2019)
Journal Article
Casas, L., & Mitchell, K. (2019). Intermediated Reality: A Framework for Communication Through Tele-Puppetry. Frontiers in Robotics and AI, 6, https://doi.org/10.3389/frobt.2019.00060

We introduce Intermediated Reality (IR), a framework for intermediated communication enabling collaboration through remote possession of entities (e.g., toys) that come to life in mobile Mediated Reality (MR). As part of a two-way conversation, each... Read More about Intermediated Reality: A Framework for Communication Through Tele-Puppetry.

Enhanced Shadow Retargeting with Light-Source Estimation Using Flat Fresnel Lenses (2019)
Journal Article
Casas, L., Fauconneau, M., Kosek, M., Mclister, K., & Mitchell, K. (2019). Enhanced Shadow Retargeting with Light-Source Estimation Using Flat Fresnel Lenses. Computers, 8(2), Article 29. https://doi.org/10.3390/computers8020029

Shadow-retargeting maps depict the appearance of real shadows to virtual shadows given corresponding deformation of scene geometry, such that appearance is seamlessly maintained. By performing virtual shadow reconstruction from unoccluded real-shadow... Read More about Enhanced Shadow Retargeting with Light-Source Estimation Using Flat Fresnel Lenses.

Deep Precomputed Radiance Transfer for Deformable Objects (2019)
Journal Article
Li, Y., Wiedemann, P., & Mitchell, K. (2019). Deep Precomputed Radiance Transfer for Deformable Objects. Proceedings of the ACM on Computer Graphics and Interactive Techniques, 2(1), Article 3. https://doi.org/10.1145/3320284

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.

Memory Allocation For Seamless Media Content Presentation (2019)
Patent
Mitchell, K., Koniaris, C., & Chitalu, F. (2019). Memory Allocation For Seamless Media Content Presentation. US20190096028

A system for performing memory allocation for seamless media content presentation includes a computing platform having a CPU, a GPU having a GPU memory, and a main memory storing a memory allocation software code. The CPU executes the memory allocati... Read More about Memory Allocation For Seamless Media Content Presentation.