REAL-TIME PROCESSING PIPELINE FOR 3D IMAGING APPLICATIONS

Most processing tasks in three-dimensional (3D) applications share common ground in terms of algorithm design and implementation. Furthermore, time consuming tasks like 3D reconstruction of objects from generic multiview images and compression of massive amounts of 3D image data, require enormous data processing power, and in many cases computations should be performed in real-time. In this paper we present a hardware architecture that jointly addresses both tasks. The proposed design features processing elements and memory modules that form a common compression and reconstruction datapath. Extensive pipelining minimizes throughput delays and memory access operations. Our implementation achieves real-time performance for both tasks, efficiently addressing demanding 3D imaging and video applications.