Interactive editing of massive imagery made simple

Summa, Brian; Scorzelli, Giorgio; Jiang, Ming; Bremer, Peer-Timo; Pascucci, Valerio

doi:10.1145/1857907.1857909

Cited by 13 publications

(21 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All previous multi-resolution volume renderers require the multi-resolution hierarchy to be built in a pre-process, which is not feasible for our scenario of dynamically streaming image data. A preprocessing step is also required by all previous systems that support streaming of volume data for progressive rendering, such as the ViSUS system [28]. The ImageVis3D/Tuvok system [19] supports both slicedbased volume rendering and ray-casting.…”

Section: Related Workmentioning

confidence: 99%

Interactive Volume Exploration of Petascale Microscopy Data Streams Using a Visualization-Driven Virtual Memory Approach

Hadwiger

Beyer

Jeong

et al. 2012

IEEE Trans. Visual. Comput. Graphics

150

View full text Add to dashboard Cite

Fig. 1.Our system is the first to enable neuroscientists to interactively explore petascale volume data resulting from high-throughput electron microscopy data streams. The volume can be visualized while the acquisition is still in progress, and without pre-processing all data into a 3D multi-resolution hierarchy as required by all previous systems. Shown here: 21, 494 ⇥ 25, 790 ⇥ 1, 850 mouse cortex.Abstract-This paper presents the first volume visualization system that scales to petascale volumes imaged as a continuous stream of high-resolution electron microscopy images. Our architecture scales to dense, anisotropic petascale volumes because it: (1) decouples construction of the 3D multi-resolution representation required for visualization from data acquisition, and (2) decouples sample access time during ray-casting from the size of the multi-resolution hierarchy. Our system is designed around a scalable multi-resolution virtual memory architecture that handles missing data naturally, does not pre-compute any 3D multi-resolution representation such as an octree, and can accept a constant stream of 2D image tiles from the microscopes. A novelty of our system design is that it is visualization-driven: we restrict most computations to the visible volume data. Leveraging the virtual memory architecture, missing data are detected during volume ray-casting as cache misses, which are propagated backwards for on-demand out-of-core processing. 3D blocks of volume data are only constructed from 2D microscope image tiles when they have actually been accessed during ray-casting. We extensively evaluate our system design choices with respect to scalability and performance, compare to previous best-of-breed systems, and illustrate the effectiveness of our system for real microscopy data from neuroscience.

show abstract

Section: Related Workmentioning

confidence: 99%

Interactive Volume Exploration of Petascale Microscopy Data Streams Using a Visualization-Driven Virtual Memory Approach

Hadwiger

Beyer

Jeong

et al. 2012

IEEE Trans. Visual. Comput. Graphics

150

View full text Add to dashboard Cite

show abstract

“…This hierarchical, multiresolution data representation is beneficial for large-scale interactive analysis and visualization [39]. However, the file format, while successful in the areas of digital photography [34] and large scale visualization [29], is inherently serial. In earlier work [17] we proposed a three-phase I/O approach to write data in parallel in IDX file format.…”

Section: Parallel Idx (Pidx)mentioning

confidence: 99%

Characterization and modeling of PIDX parallel I/O for performance optimization

Kumar

Saha

Vishwanath

et al. 2013

Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis

Self Cite

View full text Add to dashboard Cite

Parallel I/O library performance can vary greatly in response to user-tunable parameter values such as aggregator count, file count, and aggregation strategy. Unfortunately, manual selection of these values is time consuming and dependent on characteristics of the target machine, the underlying file system, and the dataset itself. Some characteristics, such as the amount of memory per core, can also impose hard constraints on the range of viable parameter values. In this work we address these problems by using machine learning techniques to model the performance of the PIDX parallel I/O library and select appropriate tunable parameter values. We characterize both the network and I/O phases of PIDX on a Cray XE6 as well as an IBM Blue Gene/P system. We use the results of this study to develop a machine learning model for parameter space exploration and performance prediction.

show abstract

“…A very powerful family of multi-scale representations are wavelets [Mallat 2009], which can be adapted to better observe edges, e.g., edge-avoiding wavelets [Fattal 2009], orà-trous wavelets [Hanika et al 2011]. Our goal, however, is the direct evaluation of non-linear operators at any desired output resolution, which enables their scalable evaluation for gigapixel images [Kopf et al 2007], whose display, filtering, and processing is an active area of current research [Kazhdan and Hoppe 2008;Summa et al 2010].…”

Section: Related Workmentioning

confidence: 99%

“…The recent increase in the resolution of acquired and computed image data has resulted in a need for novel multi-resolution techniques, e.g., representing, processing, and rendering gigapixel images [Kopf et al 2007;Summa et al 2010]. One of the most prevalent types of multiresolution image hierarchies are pyramid representations, such as mipmaps [Williams 1983], or Gaussian pyramids [Burt and Adelson 1983].…”

Section: Introductionmentioning

confidence: 99%

Sparse PDF maps for non-linear multi-resolution image operations

et al. 2012

View full text Add to dashboard Cite

Figure 1: sPDF-maps are a compact multi-resolution image pyramid data structure that sparsely encodes pre-computed pixel neighborhood probability density functions (pdfs) for all pixels in the pyramid. They enable the accurate, anti-aliased evaluation of non-linear image operators directly at any output resolution. A variety of operators can be computed at run time from the same pre-computed data structure in a way that scales to gigapixel images, such as local Laplacian filters for (b,d) detail enhancement or (c,e) smoothing, (f) median filters, (g) dominant mode filters, (h) maximum mode filters, (i) bilateral filters. The original image (a) has resolution 16, 898 × 14, 824 (250 Mpixels). AbstractWe introduce a new type of multi-resolution image pyramid for high-resolution images called sparse pdf maps (sPDF-maps). Each pyramid level consists of a sparse encoding of continuous probability density functions (pdfs) of pixel neighborhoods in the original image. The encoded pdfs enable the accurate computation of non-linear image operations directly in any pyramid level with proper pre-filtering for anti-aliasing, without accessing higher or lower resolutions. The sparsity of sPDF-maps makes them feasible for gigapixel images, while enabling direct evaluation of a variety of non-linear operators from the same representation. We illustrate this versatility for antialiased color mapping, O(n) local Laplacian filters, smoothed local histogram filters (e.g., median or mode filters), and bilateral filters.

show abstract

Interactive editing of massive imagery made simple

Cited by 13 publications

References 0 publications

Interactive Volume Exploration of Petascale Microscopy Data Streams Using a Visualization-Driven Virtual Memory Approach

Interactive Volume Exploration of Petascale Microscopy Data Streams Using a Visualization-Driven Virtual Memory Approach

Characterization and modeling of PIDX parallel I/O for performance optimization

Sparse PDF maps for non-linear multi-resolution image operations

Contact Info

Product

Resources

About