Spatial Encoding Research Group
|
|
|
This page contains a list of active research projects currently underway in the Spatial Encoding Research Group. Additional information regarding each project is accessible by clicking on the "More Information" link found after each project summary.
SWIM: Streaming of Walkthroughs for Image-Based ModelsThe SWIM project is just getting off the ground. We'll be working on new representations and streaming protocols to allow multiple users to access a remote dataset for image-based walkthroughs. Back to Top
IRW: An Incremental Representation for Image-Based WalkthroughsIRW is a new representation for interactive image-based walkthroughs. The target applications reconstruct a scene from novel viewpoints using samples from a spatial image dataset collected from a plane at eye-level. The datasets pair images with camera pose information and are often extremely large in size. Our representation exploits spatial coherence and rearranges the input samples as epipolar images. The base unit corresponds to a column of the original image that can be individually addressed and accessed. The overall representation, IRW, supports incremental updates, efficient encoding, scalable performance, and selective inclusion used by different reconstruction algorithms. Back to Top
Spatially Encoded Far-Field Representations for Interactive WalkthroughsWe introduce the notion of spatially encoded video and use it for efficiently representing image-based impostors for interactive walkthroughs. As part of a pre-process, we automatically decompose the model and compute the far-fields. The resulting texture images are organized along multiple dimensions and can be accessed in a user-steered order at interactive rates. Our encoding algorithm can compress the impostors size by two orders of magnitude. Furthermore, the storage cost for additional impostors or samples grows sub-linearly. The resulting system has been applied to a complex CAD environment composed of 13 million triangles. We are able to render it at interactive rates on a PC with little loss in image quality. Back to Top |
|
--
|
