Search For:

Displaying 1-31 out of 31 total
Network Protocol for I teraction and Scalable Distributed Visualization
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Jan-Michael Frahm, Jan-Friso Evers-Senne, Reinhard Koch
Issue Date:June 2002
pp. 44
In the last decade the visualization of virtual environments and interaction within was possible only with specialized hardware. This hardware was very expensive, had a lack of scalability and used specific protocols, busses, networks for communication and...
 
USAC: A Universal Framework for Random Sample Consensus
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Rahul Raguram,Ondrej Chum,Marc Pollefeys,Jiri Matas,Jan-Michael Frahm
Issue Date:August 2013
pp. 2022-2038
A computational problem that arises frequently in computer vision is that of estimating the parameters of a model from data that have been contaminated by noise and outliers. More generally, any practical system that seeks to estimate quantities from noisy...
 
On the Privacy Risks of Virtual Keyboards: Automatic Reconstruction of Typed Input from Compromising Reflections
Found in: IEEE Transactions on Dependable and Secure Computing
By Rahul Raguram,Andrew M. White,Yi Xu,Jan-Michael Frahm,Pierre Georgel,Fabian Monrose
Issue Date:May 2013
pp. 154-167
We investigate the implications of the ubiquity of personal mobile devices and reveal new techniques for compromising the privacy of users typing on virtual keyboards. Specifically, we show that so-called compromising reflections (in, for example, a victim...
 
Increasing the Efficiency of Local Stereo by Leveraging Smoothness Constraints
Found in: 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)
By Yilin Wang,Enrique Dunn,Jan-Michael Frahm
Issue Date:October 2012
pp. 246-253
We introduce a novel framework for efficient stereo disparity estimation leveraging the spatial smoothness typically assumed in stereo and formalized by the various smoothness constraints. The smoothness constraint presumes that a neighboring set of pixels...
 
Room-sized informal telepresence system
Found in: Virtual Reality Conference, IEEE
By Mingsong Dou,Ying Shi,Jan-Michael Frahm,Henry Fuchs,Bill Mauchly,Mod Marathe
Issue Date:March 2012
pp. 15-18
We present a room-sized telepresence system for informal gatherings rather than conventional meetings. Unlike conventional systems which constrain participants to sit in fixed positions, our system aims to facilitate casual conversations between people in ...
 
RECON: Scale-adaptive robust estimation via Residual Consensus
Found in: Computer Vision, IEEE International Conference on
By Rahul Raguram,Jan-Michael Frahm
Issue Date:November 2011
pp. 1299-1306
In this paper, we present a novel, threshold-free robust estimation framework capable of efficiently fitting models to contaminated data. While RANSAC and its many variants have emerged as popular tools for robust estimation, their performance is largely d...
 
A geometric solver for calibrated stereo egomotion
Found in: Computer Vision, IEEE International Conference on
By Enrique Dunn,Brian Clipp,Jan-Michael Frahm
Issue Date:November 2011
pp. 1187-1194
This paper introduces a novel geometrical solution for the pose estimation of a stereo camera system as commonly used in robotics, where the camera system balances between coverage and overlap. The proposed approach considers a set of features observed, re...
 
Online environment mapping
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jongwoo Lim,Jan-Michael Frahm,M. Pollefeys
Issue Date:June 2011
pp. 3489-3496
The paper proposes a vision based online mapping of large-scale environments. Our novel approach uses a hybrid representation of a fully metric Euclidean environment map and a topological map. This novel hybrid representation facilitates our scalable onlin...
 
Efficient Generation of Multi-perspective Panoramas
Found in: 3D Imaging, Modeling, Processing, Visualization and Transmission, International Conference on
By Enliang Zheng,Rahul Raguram,Pierre Fite-Georgel,Jan-Michael Frahm
Issue Date:May 2011
pp. 86-92
In this paper, we present an efficient technique for generating multi-perspective panoramic images of long scenes. The input to our system is a video sequence captured by a moving camera navigating through a long scene, and our goal is to efficiently gener...
 
An Approach for Shape from Surface Normals with Local Discontinuity Detection
Found in: 3D Imaging, Modeling, Processing, Visualization and Transmission, International Conference on
By Yilin Wang,Enrique Dunn,Jan-Michael Frahm
Issue Date:May 2011
pp. 188-195
We present a multi-modal surface reconstruction approach, which utilizes direct surface orientation measurements along with luminance information to obtain high quality 3D reconstructions. The proposed approach models local surface geometry as a set of int...
 
Piecewise planar and non-planar stereo for urban scene reconstruction
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By David Gallup, Jan-Michael Frahm, Marc Pollefeys
Issue Date:June 2010
pp. 1418-1425
Piecewise planar models for stereo have recently become popular for modeling indoor and urban outdoor scenes. The strong planarity assumption overcomes the challenges presented by poorly textured surfaces, and results in low complexity 3D models for render...
 
Fast gain-adaptive KLT tracking on the GPU
Found in: Computer Vision and Pattern Recognition Workshop
By Christopher Zach, David Gallup, Jan-Michael Frahm
Issue Date:June 2008
pp. 1-7
High-performance feature tracking from video input is a valuable tool in many computer vision techniques and mixed reality applications. This work presents a refined and substantially accelerated approach to KLT feature tracking performed on the GPU. Addit...
 
3D model search and pose estimation from single images using VIP features
Found in: Computer Vision and Pattern Recognition Workshop
By Changchang Wu, Friedrich Fraundorfer, Jan-Michael Frahm, Marc Pollefeys
Issue Date:June 2008
pp. 1-8
This paper describes a method to efficiently search for 3D models in a city-scale database and to compute the camera poses from single query images. The proposed method matches SIFT features (from a single image) to viewpoint invariant patches (VIP) from a...
 
Variable baseline/resolution stereo
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By David Gallup, Jan-Michael Frahm, Philippos Mordohai, Marc Pollefeys
Issue Date:June 2008
pp. 1-8
We present a novel multi-baseline, multi-resolution stereo method, which varies the baseline and resolution proportionally to depth to obtain a reconstruction in which the depth error is constant. This is in contrast to traditional stereo, in which the err...
 
Simple calibration of non-overlapping cameras with a mirror
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Ram Krishan Kumar, Adrian Ilie, Jan-Michael Frahm, Marc Pollefeys
Issue Date:June 2008
pp. 1-7
Calibrating a network of cameras with non-overlapping views is an important and challenging problem in computer vision. In this paper, we present a novel technique for camera calibration using a planar mirror. We overcome the need for all cameras to see a ...
 
3D model matching with Viewpoint-Invariant Patches (VIP)
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Changchang Wu, Brian Clipp, Xiaowei Li, Jan-Michael Frahm, Marc Pollefeys
Issue Date:June 2008
pp. 1-8
The robust alignment of images and scenes seen from widely different viewpoints is an important challenge for camera and scene reconstruction. This paper introduces a novel class of viewpoint independent local features for robust registration and novel alg...
 
Radiometric calibration with illumination change for outdoor scene analysis
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Seon Joo Kim, Jan-Michael Frahm, Marc Pollefeys
Issue Date:June 2008
pp. 1-8
The images of an outdoor scene collected over time are valuable in studying the scene appearance variation which can lead to novel applications and help enhance existing methods that were constrained to controlled environments. However, the images do not r...
 
Robust 6DOF Motion Estimation for Non-Overlapping, Multi-Camera Systems
Found in: Applications of Computer Vision, IEEE Workshop on
By Brian Clipp, Jae-Hak Kim, Jan-Michael Frahm, Marc Pollefeys, Richard Hartley
Issue Date:January 2008
pp. 1-8
This paper introduces a novel, robust approach for 6DOF motion estimation of a multi-camera system with non-overlapping views. The proposed approach is able to solve the pose estimation, including scale, for a two camera system with non-overlapping views. ...
 
Joint Feature Tracking and Radiometric Calibration from Auto-Exposure Video
Found in: Computer Vision, IEEE International Conference on
By Seon Joo Kim, Jan-Michael Frahm, Marc Pollefeys
Issue Date:October 2007
pp. 1-8
To capture the full brightness range of natural scenes, cameras automatically adjust the exposure value which causes the brightness of scene points to change from frame to frame. Given such a video sequence, we introduce a new method for tracking features ...
 
Evaluation of Large Scale Scene Reconstruction
Found in: Computer Vision, IEEE International Conference on
By Paul Merrell, Philippos Mordohai, Jan-Michael Frahm, Marc Pollefeys
Issue Date:October 2007
pp. 1-8
We present an evaluation methodology and data for large scale video-based 3D reconstruction. We evaluate the effects of several parameters and draw conclusions that can be useful for practical systems operating in uncontrolled environments Unlike the bench...
 
Real-Time Visibility-Based Fusion of Depth Maps
Found in: Computer Vision, IEEE International Conference on
By Paul Merrell, Amir Akbarzadeh, Liang Wang, Philippos Mordohai, Jan-Michael Frahm, Ruigang Yang, David Nister, Marc Pollefeys
Issue Date:October 2007
pp. 1-8
We present a viewpoint-based approach for the quick fusion of multiple stereo depth maps. Our method selects depth estimates for each pixel that minimize violations of visibility constraints and thus remove errors and inconsistencies from the depth maps to...
 
Differential Camera Tracking through Linearizing the Local Appearance Manifold
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Hua Yang, Marc Pollefeys, Greg Welch, Jan-Michael Frahm, Adrian Ilie
Issue Date:June 2007
pp. 1-8
The appearance of a scene is a function of the scene contents, the lighting, and the camera pose. A set of n-pixel images of a non-degenerate scene captured from different perspectives lie on a 6D nonlinear manifold in Rn. In general, this nonlinear manifo...
 
Tutorials - MAR Tutorial 1 (half day) & ISMAR Tutorial 2 (half day)
Found in: Mixed and Augmented Reality, IEEE / ACM International Symposium on
By Jan-michael Frahm, Jannick Rolland, Andrei State, Ozan Cakmakci
Issue Date:October 2006
pp. xxi
No summary available.
   
RANSAC for (Quasi-)Degenerate data (QDEGSAC)
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jan-Michael Frahm, Marc Pollefeys
Issue Date:June 2006
pp. 453-460
The computation of relations from a number of potential matches is a major task in computer vision. Often RANSAC is employed for the robust computation of relations such as the fundamental matrix. For (quasi-)degenerate data however, it often fails to comp...
 
Camera Calibration with Known Rotation
Found in: Computer Vision, IEEE International Conference on
By Jan-Michael Frahm, Reinhard Koch
Issue Date:October 2003
pp. 1418
We address the problem of using external rotation information with uncalibrated video sequences. The main problem addressed is, what is the benefit of the orientation infomation for camera calibration? It is shown that in case of a rotating camera the came...
 
Real-Time Plane-Sweeping Stereo with Multiple Sweeping Directions
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By David Gallup, Jan-Michael Frahm, Philippos Mordohai, Qingxiong Yang, Marc Pollefeys
Issue Date:June 2007
pp. 1-8
Recent research has focused on systems for obtaining automatic 3D reconstructions of urban env ironments from video acquired at street level. These systems record enormous amounts of video; therefore a key component is a stereo matcher which can process th...
 
Combining semantic scene priors and haze removal for single image depth estimation
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Ke Wang,Enrique Dunn,Joseph Tighe,Jan-Michael Frahm
Issue Date:March 2014
pp. 800-807
We consider the problem of estimating the relative depth of a scene from a monocular image. The dark channel prior, used as a statistical observation of haze free images, has been previously leveraged for haze removal and relative depth estimation tasks. H...
   
Rotation estimation from cloud tracking
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Sangwoo Cho,Enrique Dunn,Jan-Michael Frahm
Issue Date:March 2014
pp. 917-924
We address the problem of online relative orientation estimation from streaming video captured by a sky-facing camera on a mobile device. Namely, we rely on the detection and tracking of visual features attained from cloud structures. Our proposed method a...
   
Personal Photograph Enhancement Using Internet Photo Collections
Found in: IEEE Transactions on Visualization and Computer Graphics
By Chenxi Zhang, Jizhou Gao,Oliver Wang,Pierre Georgel, Ruigang Yang,James Davis,Jan-Michael Frahm,Marc Pollefeys
Issue Date:February 2014
pp. 262-275
Given the growth of Internet photo collections, we now have a visual index of all major cities and tourist sites in the world. However, it is still a difficult task to capture that perfect shot with your own camera when visiting these places, especially wh...
 
Security Analysis and Related Usability of Motion-based CAPTCHAs: Decoding Codewords in Motion
Found in: IEEE Transactions on Dependable and Secure Computing
By Yi Xu,Gerardo Reynaga,Sonia Chiasson,Jan-Michael Frahm,Fabian Monrose,Paul Van Oorschot
Issue Date:December 2013
pp. 1
We explore the robustness and usability of moving-image object recognition (video) CAPTCHAs, designing and implementing automated attacks based on computer vision techniques. Our approach is suitable for broad classes of moving-image CAPTCHAs involving rig...
 
Seeing double: reconstructing obscured typed input from repeated compromising reflections
Found in: Proceedings of the 2013 ACM SIGSAC conference on Computer & communications security (CCS '13)
By Andrew M. White, Jared Heinly, Yi Xu, Fabian Monrose, Jan-Michael Frahm
Issue Date:November 2013
pp. 1063-1074
Of late, threats enabled by the ubiquitous use of mobile devices have drawn much interest from the research community. However, prior threats all suffer from a similar, and profound, weakness - namely the requirement that the adversary is either within vis...
     
 1