Graf, HolgerHolgerGrafHazke, LeonLeonHazkeKahn, SvenjaSvenjaKahnMalerczyk, CorneliusCorneliusMalerczyk2022-03-112022-03-112011https://publica.fraunhofer.de/handle/publica/37191510.1007/978-3-642-21799-9_32In this paper we present a new framework for an accelerated 3D reconstruction of deformable objects within a multi-view setup. It is based on a new memory management and an enhanced algorithm pipeline of the well known Image-Based Visual Hull (IBVH) algorithm that enables efficient and fast reconstruction results and opens up new perspectives for the scalability of time consuming computations within larger camera environments. As a result, a significant increase of frame rates for the volumetric reconstruction of deformable objects can be achieved using an optimized CUDA-based implementation on NVIDIA's Fermi-GPUs.enGraphics Processing Unit (GPU)Compute Unified Device Architecture (CUDA)3D reconstruction006Accelerated real-time reconstruction of 3D deformable objects from multi-view video channelsconference paper