Abstract:
For compression, we propose an overcomplete multiview imagery representation. We use rate-distortion (R-D) to decompose multiview datasets into additive diffuse and specular content. We use an R-D inspired cost function to drive the compressibility-based decomposition and different sparsifying transforms for diffuse and specular components.
We first present a framework that separates data in a registered domain to avoid view warping. Next, specular data is separated from multiple reference view coordinates using a more comprehensive method. Synthetic datasets have a coding gain of 0.6 dB, while real datasets have 0.9 dB.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
