All Outputs (6)

Method for Efficient CPU-GPU Streaming for Walkthrough of Full Motion Lightfield Video (2017)
Conference Proceeding
Chitalu, F. M., Koniaris, B., & Mitchell, K. (2017). Method for Efficient CPU-GPU Streaming for Walkthrough of Full Motion Lightfield Video. In CVMP 2017: Proceedings of the 14th European Conference on Visual Media Production (CVMP 2017). https://doi.org/10.1145/3150165.3150173

Lightfield video, as a high-dimensional function, is very demanding in terms of storage. As such, lightfield video data, even in a compressed form, do not typically fit in GPU or main memory unless the capture area, resolution or duration is sufficie... Read More about Method for Efficient CPU-GPU Streaming for Walkthrough of Full Motion Lightfield Video.

IRIDiuM+: deep media storytelling with non-linear light field video (2017)
Conference Proceeding
Kosek, M., Koniaris, B., Sinclair, D., Markova, D., Rothnie, F., Smoot, L., & Mitchell, K. (2017). IRIDiuM+: deep media storytelling with non-linear light field video. In SIGGRAPH '17 ACM SIGGRAPH 2017 VR Village. https://doi.org/10.1145/3089269.3089277

We present immersive storytelling in VR enhanced with non-linear sequenced sound, touch and light. Our Deep Media (Rose 2012) aim is to allow for guests to physically enter rendered movies with novel non-linear storytelling capability. With the ab... Read More about IRIDiuM+: deep media storytelling with non-linear light field video.

Real-time rendering with compressed animated light fields. (2017)
Conference Proceeding
Koniaris, B., Kosek, M., Sinclair, D., & Mitchell, K. (2017). Real-time rendering with compressed animated light fields. In GI '17 Proceedings of the 43rd Graphics Interface Conference (33-40). https://doi.org/10.20380/GI2017.05

We propose an end-to-end solution for presenting movie quality animated graphics to the user while still allowing the sense of presence afforded by free viewpoint head motion. By transforming offline rendered movie content into a novel immersive repr... Read More about Real-time rendering with compressed animated light fields..

Real-Time Multi-View Facial Capture with Synthetic Training (2017)
Journal Article
Klaudiny, M., McDonagh, S., Bradley, D., Beeler, T., & Mitchell, K. (2017). Real-Time Multi-View Facial Capture with Synthetic Training. Computer Graphics Forum, 36(2), 325-336. https://doi.org/10.1111/cgf.13129

We present a real-time multi-view facial capture system facilitated by synthetic training imagery. Our method is able to achieve high-quality markerless facial performance capture in real-time from multi-view helmet camera data, employing an actor sp... Read More about Real-Time Multi-View Facial Capture with Synthetic Training.

Noise Reduction on G-Buffers for Monte Carlo Filtering: Noise Reduction on G-Buffers for Monte Carlo Filtering (2017)
Journal Article
Moon, B., Iglesias-Guitian, J. A., McDonagh, S., & Mitchell, K. (2017). Noise Reduction on G-Buffers for Monte Carlo Filtering: Noise Reduction on G-Buffers for Monte Carlo Filtering. Computer Graphics Forum, 36(8), 600-612. https://doi.org/10.1111/cgf.13155

We propose a novel pre-filtering method that reduces the noise introduced by depth-of-field and motion blur effects in geometric buffers (G-buffers) such as texture, normal and depth images. Our pre-filtering uses world positions and their variances... Read More about Noise Reduction on G-Buffers for Monte Carlo Filtering: Noise Reduction on G-Buffers for Monte Carlo Filtering.

Rapid one-shot acquisition of dynamic VR avatars (2017)
Conference Proceeding
Malleson, C., Kosek, M., Klaudiny, M., Huerta, I., Bazin, J., Sorkine-Hornung, A., …Mitchell, K. (2017). Rapid one-shot acquisition of dynamic VR avatars. In IEEE 2017 Virtual Reality (VR). https://doi.org/10.1109/vr.2017.7892240

We present a system for rapid acquisition of bespoke, animatable, full-body avatars including face texture and shape. A blendshape rig with a skeleton is used as a template for customization. Identity blendshapes are used to customize the body and fa... Read More about Rapid one-shot acquisition of dynamic VR avatars.