Parallel high resolution real-time Visual Hull on GPU

Waizenegger, Wolfgang; Feldmann, Ingo; Eisert, Peter; Kauff, Peter

doi:10.1109/icip.2009.5413661

Cited by 18 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Volume carving on the GPU is straight-forward (and as mentioned, previously studied, see for instance [7,8,9,10]). The multiple texture fetches involved in processing each voxel means that the algorithm is completely I/Obound, so there is no significant overhead in correcting for distortion.…”

Section: Volume Carvingmentioning

confidence: 86%

“…In [7], two GPU based visual hull computation algorithms were proposed, where the resulting 3D reconstruction method is able to operate at 30 fps with 16 cameras and 4 PCs. In [8], a single GPU implementation is used for a realtime 3D video conferencing application, where a new cache strategy was developed for parallel calculation of visual hulls and a factor of five speedup was reported. A CUDA-accelerated realtime 3D modeling system is presented in [9], which offers accurate visual hull reconstruction with texture mapping, at a frame rate of 20 fps.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Real-time online camera synchronization for volume carving on GPU

Haufmann

Brodtkorb

Berge

et al. 2013

2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance

View full text Add to dashboard Cite

Volume carving is a well-known technique for reconstructing a 3D scene from a set of 2D images, using features detected in individual cameras, and camera parameters. Spatial calibration of the cameras is well understood, but the resulting carved volume is very sensitive to temporal offsets between the cameras. Automatic synchronization between the cameras is therefore desirable. In this paper, we present a highly efficient implementation of volume carving and synchronization on a heterogeneous system fitted with commodity GPUs using an improved version of the algorithm in [1].An online, real-time synchronization system is described and evaluated on surveillance video of an indoor scene. Improvements to the state of the art CPU-based algorithms are described.978-1-4799-0703-8/13/$31.00 ©2013 IEEE

show abstract

Section: Volume Carvingmentioning

confidence: 86%

Section: Related Workmentioning

confidence: 99%

Real-time online camera synchronization for volume carving on GPU

Haufmann

Brodtkorb

Berge

et al. 2013

2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance

View full text Add to dashboard Cite

show abstract

“…(Matusik et al, 2000) and (Li et al, 2004) adopt complex hardware like multi-processors and distributed system to do this step to guarantee the VH computation in real-time. There are many GPU-based methods (Ladikos et al, 2008;Waizenegger et al, 2009;Yous et al, 2007) to accelerate the visual hull computation, for the VH algorithm is highly parallel. Thus, it is natural to think if the preprocessing can be parallelized, too.…”

Section: Image Vectorization In Applicationsmentioning

confidence: 99%

Real-time Image Vectorization on GPU

Xiong

Feng

Zhou

2016

Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

View full text Add to dashboard Cite

In this paper, we present a novel algorithm to convert a raster image into its vector form. Different from the state-of-art methods, we explore the potential parallelism that exists in the problem and propose an algorithm suitable to be accelerated by the graphics hardware. In our algorithm, the vectorization task is decomposed into four steps: detecting the boundary pixels, pre-computing the connectivity relationship of detected pixels, organizing detected pixels into boundary loops and vectorizing each loop into line segments. The boundary detection and connectivity pre-computing are parallelized owing to the independence between scanlines. After a sequential boundary pixels organizing, all loops are vectorized concurrently. With a GPU implementation, the vectorization can be accomplished in real-time. Then, the image can be represented by the vectorized contour. This real-time vectorization algorithm can be used on images with multiple silhouettes and multiview videos. We demonstrate the efficiency of our algorithm with several applications including cartoon and document vectorization.

show abstract

“…However, true real-time processing of such data is still a challenging task. Only recent developments in GPU computing have made it possible to render virtual viewpoints at interactive frame rates [18], but often exceed the computational power of one computer [16].…”

Section: Related Workmentioning

confidence: 99%

“…However, such systems generally do not allow one to simulate a correct mirror because video devices are only able to capture a projected image and not the reflection of the user from his viewpoint. Free viewpoint video systems on the other hand are able to render an arbitrary view of a person by combining images from multiple fixed cameras [3,9,18]. This allows for the accurate simulation of optical effects, including rendering of a reflection image.…”

Section: Introductionmentioning

confidence: 99%

A Free-Viewpoint Virtual Mirror with Marker-Less User Interaction

et al. 2011

View full text Add to dashboard Cite

We present a Virtual Mirror system which is able to simulate a physically correct full-body mirror on a monitor. In addition, users can freely rotate the mirror image which allows them to look at themselves from the side or from the back, for example. This is achieved through a multiple camera system and visual hull based rendering. A real-time 3D reconstruction and rendering pipeline enables us to create a virtual mirror image at 15 frames per second on a single computer. Moreover, it is possible to extract a three dimensional skeleton of the user which is the basis for marker-less interaction with the system.

show abstract

Parallel high resolution real-time Visual Hull on GPU

Cited by 18 publications

References 11 publications

Real-time online camera synchronization for volume carving on GPU

Real-time online camera synchronization for volume carving on GPU

Real-time Image Vectorization on GPU

A Free-Viewpoint Virtual Mirror with Marker-Less User Interaction

Contact Info

Product

Resources

About