Ioannis Stamos

Ioannis Stamos
City University of New York - Hunter College | Hunter CUNY · Department of Computer Science

PhD

About

55
Publications
6,974
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,961
Citations
Citations since 2016
9 Research Items
465 Citations
2016201720182019202020212022020406080
2016201720182019202020212022020406080
2016201720182019202020212022020406080
2016201720182019202020212022020406080
Additional affiliations
November 2013 - June 2014
Google Inc.
Position
  • Visiting Scientist
September 2001 - present
City University of New York - Hunter College
Position
  • Professor (Full)
September 2001 - present
CUNY Graduate Center
Position
  • Professor (Full)

Publications

Publications (55)
Article
This paper presents a systematic approach to the problem of photorealistic 3-D model acquisition from the combination of range and image sensing. The input is a sequence of unregistered range scans of the scene and a sequence of unregistered 2-D photographs of the same scene. The output is a true texture-mapped geometric model of the scene. We beli...
Conference Paper
Full-text available
Laser range scanners provide rich 3D representations of urban scenes. These scenes are replete with repetitive architectural features such as windows, balconies, and cornices. Processing of dense 3D images is often computationally intensive and occurs offline after acquisition. Here, however, we present an online algorithm for the detection of repe...
Preprint
Full-text available
Transfer learning is widely used in computer vision (CV), natural language processing (NLP) and achieves great success. Most transfer learning systems are based on the same modality (e.g. RGB image in CV and text in NLP). However, the cross-modality transfer learning (CMTL) systems are scarce. In this work, we study CMTL from 2D to 3D sensor to exp...
Article
Full-text available
Instance segmentation and object detection are significant problems in the fields of computer vision and robotics. We address those problems by proposing a novel object segmentation and detection system. First, we detect 2D objects based on RGB, depth only, or RGB-D images. A 3D convolutional-based system, named Frustum VoxNet, is proposed. This sy...
Preprint
Recently, there have been a plethora of classification and detection systems from RGB as well as 3D images. In this work, we describe a new 3D object detection system from an RGB-D or depth-only point cloud. Our system first detects objects in 2D (either RGB, or pseudo-RGB constructed from depth). The next step is to detect 3D objects within the 3D...
Article
Full-text available
Repeated patterns (such as windows, balconies, and doors) are prominent and significant features in urban scenes. Therefore, detection of these repeated patterns becomes very important for city scene analysis. This paper attacks the problem of repeated pattern detection in a precise, efficient and automatic way, by combining traditional feature ext...
Chapter
This chapter presents a sequence of CUSUM stopping rules to construct an online trading strategy. It begins the analysis by describing a general trading strategy based on following upward or downward trends in a data stream, without specifying the timing mechanism behind such a strategy. The chapter builds a timing scheme stemming from quickest det...
Conference Paper
One of the most significant problems in the area of 3D range image processing is that of segmentation and classification from 3D laser range data, especially in real-time. In this work we introduce a novel multi-layer approach to the classification of 3D laser scan data. In particular, we build a hierarchical framework of online detection and ident...
Article
Unprecedented amounts of 3D data can be acquired in urban environments, but their use for scene understanding is challenging due to varying data resolution and variability of objects in the same class. An additional challenge is due to the nature of the point clouds themselves, since they lack detailed geometric or semantic information that would a...
Conference Paper
Repeated patterns (such as windows, tiles, balconies and doors) are prominent and significant features in urban scenes. Therefore, detection of these repeated patterns becomes very important for city scene analysis. This paper attacks the problem of repeated patterns detection in a precise, efficient and automatic way, by combining traditional feat...
Conference Paper
Full-text available
We present a method for discovering the structure of trees in 3D point clouds by linking wavelets with shape grammars. Given a range scan of a tree we find a grammar that can reproduce that tree, and others like it, with sub-voxel accuracy. The grammar inferred is stochastic, allowing us to generate many permutations of related trees. The method of...
Article
Full-text available
Laser range scans of urban areas have a distinctive geometry dominated by facade and ground planes and repetitive regular fenestration. Detection of these ubiquitous features provides profound insights into the scene. We present a novel method for detecting major planes and repetitive architectural features. Armed with this knowledge we illustrate...
Conference Paper
Full-text available
The current technology in stationary laser range-scanning enables high-resolution acquisition of 3D data in a sequential fashion. Traditionally, range scans are processed offline after acquisition, which significantly slows down the procedure. In this work we alleviate this limitation by developing low-complexity, online detection and classificatio...
Conference Paper
We present an online method for filling holes in point clouds by exploiting the regularity of urban areas. Sweeping a plane across the scene we compute periodicity, major planes, and occlusions. Extending rays from the laser that have been occluded gives a planar approximation for holes in facades. The periodicity of the architecture is used to vas...
Conference Paper
Full-text available
Laser range scanners have now the ability to acquire millions of 3D points of highly detailed and geometrically complex urban sites, opening new avenues of exploration in modeling urban environments. However, raw data are dense and complex, lacking high-level descriptive power, thus revealing the need for the automatic detection of architectural ob...
Article
Full-text available
The photorealistic modeling of large-scale objects, such as urban scenes, requires the combination of range sensing technology and digital photography. In this paper, we attack the key problem of camera pose estimation, in an automatic and efficient way. First, the camera orientation is recovered by matching vanishing points (extracted from 2D imag...
Article
Full-text available
Laser range scanners have now the ability to acquire millions of 3D points of highly detailed and geometrically complex urban sites, opening new avenues of exploration in modeling urban environments. In the traditional modeling pipeline, range scans are processed off-line after acquisi-tion. The slow sequential acquisition though is a bottle-neck....
Article
Full-text available
a) acquisition (b) clustering (c) refinement Figure 1. Segmentation pipeline. (a) In this simulated LIDAR setup, the frustum represents a scanner projecting a beam onto a 3D model. The beam strikes the nearest surface and measures the distance, rendered here in false color. (b) Similarity based on local plane fitting drives a hierarchical clusterin...
Conference Paper
The automatic creation of photorealistic models of large-scale scenes is an important problem. A new generation of laser range scanners can produce very accurate and dense geometric representations in terms of point clouds of 3D points. One the other hand, images captured by inexpensive regular 2D cameras can populate this geometric representation...
Article
Full-text available
This work compares the performance of all existing 2-CUSUM stopping rules used in the problem of sequential detection of a change in the drift of a Brownian motion in the case of two-sided alternatives. As a performance measure an extended Lorden criterion is used. According to this criterion the optimal stopping rule is an equalizer rule. This pap...
Article
Full-text available
The photorealistic modeling of large-scale scenes, such as urban structures, requires a fusion of range sensing technology and traditional digital photography. This paper presents a system that integrates automated 3D-to-3D and 2D-to-3D registration techniques, with multiview geometry for the photorealistic modeling of urban scenes. The 3D range sc...
Conference Paper
Full-text available
We present fast and accurate segmentation algorithms of range images of urban scenes. The utilization of these algorithms is essential as a pre-processing step for a variety of tasks, that include 3D modeling, registration, or object recognition. The accuracy of the segmentation module is critical for the performance of these higher-level tasks. In...
Conference Paper
The photorealistic modeling of large-scale objects, such as urban scenes, requires the combination of range sensing technology and digital photography. In this paper, we attack the key problem of camera pose estimation, in an automatic and efficient way. First, the camera orientation is recovered by matching vanishing points (extracted from 2D imag...
Conference Paper
Full-text available
Range sensing technology allows the photorealistic mod- eling of large-scale scenes, such as urban structures. The generated 3D representations, after automated registration, are useful for urban planning, historical preservation, or vir- tual reality applications. One major issue in 3D modeling of complex large-scale scenes is that the final resul...
Conference Paper
Full-text available
Range sensing technology allows the photo-realistic model- ing of large-scale scenes, such as urban structures. A major bottleneck in the process of 3D scene acquisition is the auto- mated registration of a large number of geometrically com- plex 3D range scans in a common frame of reference. The generated 3D representations, after automated regist...
Conference Paper
Full-text available
This paper presents a novel and efficient algorithm for the 3D range to 2D image registration problem in urban scene settings. Our input is a set of unregistered 3D range scans and a set of unregistered and uncalibrated 2D images of the scene. The 3D range scans and 2D images capture real scenes in extremely high detail. A new automated algorithm c...
Conference Paper
Full-text available
This work describes an efficient 3D modeling method from 3D range data-sets that is utilizing range data segmentation. Our algorithm starts with a set of unregistered 3D range scans of a large scale scene. The scans are being preprocessed for noise removal and hole filling. The next step is range segmentation and the extraction of planar and linear...
Article
Full-text available
We discuss new methods for building 3D models of historic sites. Our algorithm automatically computes pairwise registrations between individual scans, builds a topological graph, and places the scans in the same frame of reference.
Conference Paper
Full-text available
We are building a system that can automatically acquire 3D range scans and 2D images to build geometrically and photometrically correct 3D models of urban environments. A major bottleneck in the process is the automated registration of a large number of geometrically complex 3D range scans in a common frame of reference. In this paper we provide a...
Conference Paper
Full-text available
Preserving cultural heritage and historic sites is an important problem. These sites are subject to erosion, vandalism, and as long-lived artifacts, they have gone through many phases of construction, damage and repair. It is important to keep an accurate record of these sites using 3-D model building technology as they currently are, so preservati...
Conference Paper
Full-text available
Preserving cultural heritage and historic sites is an important problem. These sites are subject to erosion, vandalism, and as long-lived artifacts, they have gone through many phases of construction, damage and repair. It is important to keep an accurate record of these sites using 3-D model building technology as they currently are, so preservati...
Conference Paper
We are building a system that can automatically acquire 3D range scans and 2D images to build geometrically correct, texture mapped 3D models of urban environments. This paper deals with the problem of automatically registering the 3D range scans with images acquired at other times and with unknown camera calibration and location. The method involv...
Conference Paper
This paper is an overview of the AVENUE project at Columbia University. AVENUE's main goal is to automate the site modeling process in urban environments. The first component of AVENUE is a 3-D modeling system which constructs complete 3-D geometric models with photometric texture mapping acquired from different viewpoints. The second component is...
Article
Full-text available
This paper describes an interactive sensor planning system that can be used to select viewpoints subject to camera visibility, field of view and task constraints. Application areas for this method include surveillance planning, safety monitoring, architectural site design planning, and automated site modeling. Given a description of the sensor's ch...
Article
Full-text available
3-D models of complex environments, known as site models, are used in many different applications ranging from city planning, urban design, fire and police planning, military applications, virtual reality modeling and others. Site models are typically created by hand in a painstaking and error prone process. This paper focuses on two important prob...
Conference Paper
Full-text available
The automated extraction of photo-realistic 3D models of the world that can be used in applications such as virtual reality, tele-presence, digital cinematography and urban planning, is the focus of this paper. The combination of range (dense depth estimates) and image sensing (color information) provides data-sets which allow us to create photo-re...
Conference Paper
This paper deals with the automated creation of geometric and photometric correct 3-D models of the world. Those models can be used for virtual reality, tele-presence, digital cinematography and urban planning applications. The combination of range (dense depth estimates) and image sensing (color information) provides data-sets which allow us to cr...
Conference Paper
Full-text available
We present an incremental system that builds accurate CAD models of objects from multiple range images. Using a hybrid of surface mesh and volumetric representations, the system creates a “water-tight” 3D model at each step of the modeling process, allowing reasonable models to be built from a small number of views. We also present a method that ca...
Conference Paper
In this paper we present a method for automatically constructing a CAD model of an unknown object from range images. The method is an incremental one that interleaves a sensing operation that acquires and merges information into the model with a planning phase to determine the next sensor position or “view”. This is accomplished by integrating a sy...
Article
Full-text available
In this paper we present a method for automatically constructing a CAD model of an unknown object from range images. The method is an incremental one that interleaves a sensing operation that acquires and merges information into the model with a planning phase to determine the next sensor position or "view". This is accomplished by integrating a sy...
Article
Full-text available
This paper deals with the automated creation of ge-ometric and photometric correct 3-D models of the world. Those models can be used for virtual reality, tele– presence, digital cinematography and urban planning ap-plications. The combination of range (dense depth esti-mates) and image sensing (color information) provides data–sets which allow us t...
Article
Full-text available
The photorealistic modeling of large-scale scenes, such as urban structures, requires a fusion of range sensing technology and traditional digital photography. This paper summarizes the contributions of our group in that area. We present a system that integrates automated 3D-to-3D and 2D-to-3D registration techniques, with multiview geometry for th...
Article
Full-text available
The photorealistic modeling of large-scale scenes, such as urban structures, requires a fusion of range sensing tech- nology and traditional digital photography. This paper presents a system that integrates multiview geometry and automated D registration techniques for texture mapping 2D images onto 3D range data. The 3D range scans and the 2D phot...
Article
We are building a system that can automatically acquire 3D range scans and 2D images to build geo-metrically and photometrically correct 3D models of urban environments [2]. A major bottleneck in the process is the automated registration of a large number of geometrically complex 3D range scans in a com-mon frame of reference. In this paper we prov...
Article
Thesis (Ph. D.)--Columbia University, 2001. Includes bibliographical references (leaves 124-138). Department: Computer Science.

Network

Cited By

Projects

Project (1)