• Publications
  • Influence
BlinkDB: queries with bounded errors and bounded response times on very large data
TLDR
In this paper, we present BlinkDB, a massively parallel, approximate query engine for running interactive SQL queries on large volumes of data. Expand
  • 628
  • 88
  • PDF
Multicore bundle adjustment
TLDR
We present the design and implementation of new inexact Newton type Bundle Adjustment algorithms that exploit hardware parallelism for efficiently solving large scale 3D scene reconstruction problems. Expand
  • 717
  • 77
  • PDF
Building Rome in a day
TLDR
We present a system that can match and reconstruct 3D scenes from extremely large collections of photographs such as those found by searching for a given city (e.g., Rome) on Internet photo sharing sites. Expand
  • 1,003
  • 64
Generalized Non-metric Multidimensional Scaling
TLDR
We consider the non-metric multidimensional scaling problem: given a set of dissimilarities ∆, find an embedding whose inter-point Euclidean distances have the same ordering as ∆. Expand
  • 161
  • 46
  • PDF
Bundle Adjustment in the Large
TLDR
We present the design and implementation of a new inexact Newton type algorithm, which uses substantially less time and memory than standard Schur complement based methods, without compromising on the quality of the solution. Expand
  • 351
  • 42
  • PDF
Building Rome in a day
TLDR
We present a system that can match and reconstruct 3D scenes from extremely large collections of photographs such as those found by searching for a given city (e.g., Rome) on Internet photo sharing sites. Expand
  • 787
  • 39
  • PDF
Scarlett: coping with skewed content popularity in mapreduce clusters
TLDR
We present Scarlett, a system that replicates blocks based on their popularity. Expand
  • 325
  • 28
  • PDF
Higher order learning with graphs
TLDR
We argue that hypergraphs are not a natural representation for higher order relations, indeed pairwise as well ashigher order relations can be handled using graphs. Expand
  • 252
  • 27
  • PDF
Jump: virtual reality video
TLDR
We present Jump, a practical system for capturing high resolution, omnidirectional stereo (ODS) video suitable for wide scale consumption in currently available virtual reality headsets. Expand
  • 161
  • 17
  • PDF
Knowing when you're wrong: building fast and reliable approximate query processing systems
TLDR
We show that it is possible to implement a query approximation pipeline that produces approximate answers and reliable error bars at interactive speeds. Expand
  • 154
  • 16
  • PDF