|
|
Daniel G. Aliaga |
|
|
Associate
Professor of Computer Science Purdue
University 305 N.
University St. West
Lafayette, IN 47907-2066 FAX:
(765) 494-0739 Email: aliaga at cs purdue edu |
Short Biography:
Dr. Daniel G. Aliaga is an Associate Professor of Computer Science at Purdue
University. He obtained is Ph.D. degree and M.S. degree from the University of
North Carolina at Chapel Hill and his Bachelor of Science from Brown
University. Dr. Aliaga’s research is primarily in the
area of 3D computer graphics but overlaps with computer vision and with
visualization. His research area is of central importance to many critically
important industries, including computer-aided design and manufacturing,
telepresence, scientific simulations, and education. He focuses on i) 3D
urban modeling (developing novel 3D urban model acquisition methods,
forward and inverse procedural modeling, and integration with urban design and
planning), ii) projector-camera systems (focusing on spatially-augmented
reality and on appearance editing of arbitrarily shaped and colored objects),
and iii) 3D digital fabrication (in particular, on novel methods for
digital manufacturing that embed into a physical object information for a
variety of purposes, including genuinity detection,
tamper detection, and multiple appearance generation).
Dr. Aliaga has also performed research in related areas such as 3D
reconstruction, image-based rendering, rendering acceleration, and camera
design and calibration. In addition, he holds several patents related to 3D
acquisition and modeling, has designed several complete experimental research
systems, and has worked in collaboration with Bell Labs, Princeton University,
Johns Hopkins University, University of Washington, University of California
Berkeley, University of California Irvine, and University of North Carolina at
Chapel Hill. To date Prof. Aliaga has published over 70 peer reviewed
publications and chaired and served on numerous ACM and IEEE conference and
workshop committees, including being a member of more than 35 program
committees, conference chair, papers chair, invited panelist, and a frequent
reviewer of papers, journal articles, and technical courses. In addition, Dr.
Aliaga has served on several NSF panels, is on the editorial board of Graphical
Models, and is a member of ACM SIGGRAPH. His research has been whole or
partially funded by NSF, MTC, Microsoft Research, Google, and Adobe Inc.
NOTE:
on Sabbatical to ETH Zurich, Switzerland during 2011.
o Visiting Professor in Computer Vision and Geometry Group,
Department of Computer Science, ETH Zurich, 2011.
o Visiting Professor in Chair for Information Architecture,
Department of Architecture, ETH Zurich, 2011.
o Associate Professor, Purdue University, 2010-present.
o Assistant Professor, Purdue University, 2003-2010.
o Research Staff, Princeton University, 2003.
o Member of Technical Staff, Bell Labs, 1999-2002.
o Ph.D., Computer Science, University of North Carolina at Chapel Hill,
1993-1999.
o M.S., Computer Science, University of North Carolina at Chapel Hill,
1991-1993.
o B.S. Computer Science, Magna Cum Laude, Honors, Brown
University, 1987-1991.
o High School, Colegio Santa
Maria, Lima - Peru, 1982-1986.
|
Appearance
Editing: Modifying the Appearance of Real-World Objects Appearance
editing offers a unique way to view visually altered objects with various
appearances or visualizations. By carefully controlling how an object is
illuminated using digital projectors, we obtain stereoscopic imagery for any
number of observers with everything visible to the naked eye (i.e., no need
for head-mounts or goggles). Such ability is useful for various applications,
including scientific visualization, virtual restoration of cultural heritage,
and display systems. è
See blog (2011), “Digital
Restoration: Introducing an Undo Function” by Central Science (C&EN). è
See newscast (2009), “Restoring Art in an
Instant” by Discovery Breakthroughs in
Science (DBIS). |
|
|
Urban
Modeling and Visualization Our objective is to capture, simulate, and modify models
of urban environments. Today, more than half of the world’s population of 7
billion people lives in cities – and that number is
only expected to grow over the next 30 years. Cities, and urban spaces of all
sizes, are however extremely complex and their modeling is
still not solved. Our project efforts have focused on obtaining digital
models of large-scale urban structures in order to enable simulating physical
phenomena and human activities in city-size environments. To date, we have
developed several algorithms and large-scale software systems using
ground-level imagery, aerial imagery, GIS data, and forward and inverse
procedural modeling to create/modify 3D and 2D urban models. è
See documentary (2010), “Man-made
Disasters” by National Geographic Documentary as part of NatGeo Naked
Science series, appeared together with Prof. Dev
Niyogi on topic of urban sprawl and urban heat
islands. |
|
|
Embedding
Information into Physical Objects We seek to provide methods to embed into a physical
object information for a variety of purposes, including genuinity
detection, tamper detection, and multiple appearance generation. Genuinity detection refers to encoding fragile or robust
signatures so that a copy, or tampered, version can be differentiated from
the original object. Multiple appearance generation refers to generalizing
the encoded information from a signature to a different appearance of the
same physical object. The project also includes the development of underlying
infrastructure for 3D model acquisition and for appearance/signature creation
and extraction using projector-based illumination. |
|
|
A
Photogeometric Framework for Capturing 3D Objects We introduce a photogeometric
framework for acquiring 3D objects with sub-millimeter accuracy. The defining
characteristic of our framework is leveraging the complementary advantages of
photometric and geometric acquisition. The two approaches are tightly
integrated in an iterative acquisition process that achieves
self-calibration, multi-viewpoint sampling, and high level of detail. |
|
|
Conventional 3D reconstruction from digital photographs
requires (pre-calibration) or computes (self-calibration) camera pose for
each photograph. We have developed a mathematical framework where the
parameters defining camera poses are eliminated from the nonlinear system of
3-D reconstruction equations, which leads to significantly more robust and
accurate 3D models. |
|
|
Modeling
Scenes with Strong Inter-reflections Structured light is a powerful approach for acquiring 3-D
models of real world scenes. The scene is illuminated with a custom pattern
of light and imaged with a digital camera. An important challenge in
structured light acquisition comes from glossy and specular objects which
reflect the patterns of light and create false positives. We have developed
an iterative and adaptive algorithm that reduces the inter-reflection within
the scene, which leads to robust pixel classification and to accurate and
dense 3-D reconstruction. |
|
|
Modeling
Repetitive Motion in Real-World 3D Scenes Most 3-D acquisition systems assume that the scene is
static. We have taken significant steps towards supporting the acquisition of
dynamic scenes by developing algorithms that detect and leverage repetitive
motion in the scene (e.g. person walking, flag waving). Our approach produces
space-time 3D models using as few as two cameras or one camera-projector
pair. |
|
|
Occlusion-Resistant
Camera Designs: Acquiring Active Environments Obtaining image sequences of popular and active
environments is often hindered by unwanted interfering occluders.
In this work, we propose a family of Occlusion-Resistant Camera designs for
acquiring such environments. Our cameras explicitly remove interfering occluders from acquired data in real-time, during live
capture. |
|
|
We present an image-based approach to providing
interactive and photorealistic walkthroughs of complex indoor environments.
Our strategy is to obtain a dense sampling of viewpoints in a large static
environment with omnidirectional images and to replace the 3D reconstruction
challenges with easier problems of motorized-cart control, dense image-based
sampling, and compression. |
|
|
The project investigates several graphical and educational
tools using Tablet PCs. We have developed hardware and software tools for
tabletop mixed-reality and for Tablet PC applications in classrooms. |
|
|
A key component of providing realism is rendering large
and detailed 3D models at high frame rates. We explore various rendering
acceleration methods, including visibility culling, geometry simplification,
and image-based rendering. |
Current course: Spring
2012 – CS 334
|
Number |
Title |
Year |
|
CS590G/CS635 |
Capturing, Modeling, Rendering 3D Structures |
Fall 2003, Fall 2004, Spring 2007, Spring 2009, Spring 2010 |
|
CS590M |
Geometric Modeling and Applications |
|
|
CS535 |
Interactive Computer Graphics |
Fall 2005, Fall 2007, Fall
2010 |
|
CS530 |
Introduction to Scientific
Visualization |
Fall 2009 |
|
CS490G |
Tablet PC Graphics |
Spring 2004, Spring 2005, Spring
2006 |
|
CS397/CS497 |
Honor's Research |
Fall 2004 |
|
CS334 |
Fundamentals of Computer Graphics |
Spring 2008, Fall 2008, Spring 2012 |
|
CS251 |
Data Structures |
Fall 2006 |
|
CS197 |
Freshman Honor’s
Seminar |
Graduate:
Advisee’s
Carlos Vanegas (CS, PhD student)
Yi-Liu Chao (CS, PhD student)
Ignacio Garcia-Dorado (CS, PhD
student)
Ilke Demir (CS, PhD student)
Alvin Law (CS, PhD 2011, now at
Google)
Yi Xu (CS, PhD 2010, now at GE
Research)
Daniel
Bekins (CS, MS 2005, now at Electronic Arts)
Scott
Yost (CS, MS 2004, now at Microsoft)
Committee
member:
Paul
Rosen (CS, PhD 2010, Research Asst Prof @ University
of Utah)
Mihai Mudure
(CS, PhD 2008, Google)
Huiying Xu (CS, PhD 2007, Cisco)
David
Gotz (CS, PhD 2005, UNC, IBM Research)
Tyler
Smith (CS, BS 2011)
Philip
Jarvis (CS, BS 2011)
Aaron
Link (CS, BS 2009)
Robert
Insley (CS, BS 2008)
Dat Nyugen, Nitin Nalreja, Nimesh Amin (CS, BS 2006)
Paul
Ardis (CS, BS 2005, now at Univ. Rochester)
Jamie
Gennis (CS, BS 2005, now at NVIDIA)
Jonathan
Deutsch (CS, BS 2005, now at Apple Corp)
Darin
Rajan (CS, BS 2005)
o
Metropolitan Transportation Commission,
“Urban Simulation Visualization”, 2011-2012.
o
Google Research Award, (PI) “Modeling of
Buildings from Photographs”, 2011-present.
o
NSF IIS, (PI) “Integrating Behavioral,
Geometrical and Graphical Modeling to Simulate and Visualize Urban Areas”,
2010-2013.
o
NSF CNS, (PI) “A Computational Framework for
Marking Physical Objects against Counterfeiting and Tampering”, 2009-2012.
o
NSF OCI, “INTEROP: Developing Community-based
Drought Information Network Protocols and Tools for Multidisciplinary Regional
Scale Applications (DRInet)”, 2008-2012.
o
Purdue-IUPUI Applied Research Grant, (PI)
“Digital Inspection and Virtual Restoration of 3D Objects”, 2008-2009.
o
Adobe Inc., “Vector Pattern Modeling and Editing“,
2008-present.
o
PACE/Hewlett-Packard Hardware Grant, (PI)
2008.
o
NSF REU, (PI) “3D Scene Digitization”,
2006-2008.
o
NSF MSPA-MCS, (PI) “3D Scene Digitization: A
Novel Invariant Approach for Large-Scale Environment Capture”, 2004-2008.
o
Microsoft Research, (PI) “PMR: Portable Mixed
Reality”, 2005-present.
o
Microsoft Research, (PI) “MRT: A Mixed Reality
Tabletop”, 2004-present.
o Program Committee for IEEE PROCAMS
2012
o Invited Panelist for APCOSE 2011
o Program Committee for IEEE CVPR 2012
o Program Committee for ACM Symposium in
Interactive 3D Graphics 2012
o Program Committee for IEEE
Visualization 2011
o Program Committee for IEEE ICCV 2011
o Program Committee for IEEE CVPR 2011
o Program Committee for ACM Symposium in
Interactive 3D Graphics 2011
o Program Committee for IEEE PROCAMS
2010
o Program Committee ECCV Workshop on
Reconstruction and Modeling of Large-Scale 3D Virtual Environments 2010
o Program Committee for SIBGRAPI 2010
o Papers Co-Chair for ACM Symposium on Interactive 3D
Graphics and Games 2010
o Program Committee for ACM Int'l
Symposium on Mixed and Augmented Reality 2010
o Program Committee for 3DIM 2009
o Invited Panelist for IEEE PROCAMS 2009
o Program Committee for IEEE PROCAMS
2009
o Program Committee for SIBGRAPI 2009
o General Co-Chair for ACM Symposium on Interactive 3D Graphics
and Games 2009
o Program Committee for HyperText 2008
o Program Committee for Pacific Graphics
2008
o Program Committee for SIBGRAPI 2008
o Program Committee for ACM Symposium in
Interactive 3D Graphics 2008
o Student Stipend Chair for ACM Symposium on Interactive 3D
Graphics and Games 2008
o Program Committee for IEEE ICCV
Workshop on Visual Representations and Modeling of Large-scale Environments
2007
o Program Committee for ACM Int'l
Symposium on Mixed and Augmented Reality 2007
o Program Committee for Pacific Graphics
2007
o Program Committee for Symposium on
Point-based Graphics 2007
o Program Committee for SIBGRAPI 2007
o Program Committee for ACM Symposium in
Interactive 3D Graphics 2007
o Program Committee for Int'l Conference
on Computer Graphics Theory and Applications 2007
o Editor for Graphical Models
(2006-present)
o Program Committee for Symposium on
Point-based Graphics 2006
o Program Committee for ACM Int'l
Symposium on Mixed and Augmented Reality 2006
o Program Committee for Virtual Reality
Software and Technology 2006
o Program Committee for Pacific Graphics
2006
o Program Committee for ACM Symposium in
Interactive 3D Graphics 2006
o Program Committee for Int'l Conference
on Computer Graphics Theory and Applications 2006
o Program Committee for SIBGRAPI 2006
o Program Committee for Symposium on
Point-based Graphics 2005
o Program Committee for ACM Int'l
Symposium on Mixed and Augmented Reality 2005
o Program Committee for ACM Symposium in
Interactive 3D Graphics 2005
o Program Committee for Symposium on
Point-based Graphics 2004
o NSF Graphics Panel 2002
o NSF Numeric, Symbolic, and Graphic
Computation Panels 2002
o NSF Graphics Panel 2001
o ACM SIGGRAPH Course Organizer 2000
o ACM SIGGRAPH Course Organizer 1999
o Hobbies:
vintage computers, astronomy, model trains, martial arts, soccer, mountain
biking
o Languages:
English, Spanish, some German
o Family, Wedding, some
videos