ICCV 2005 - PDF Preprint Papers

ICCV 2005 IEEE International Conference on Computer Vision

3D Immersive Browsing | Click Here

Teaser Browsing | Click Here

Queue Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed ICCV-2005 Paper

click to vote

ICCV
2005
IEEE

362views Computer Vision» more ICCV 2005»

Is Levenberg-Marquardt the Most Efficient Optimization Algorithm for Implementing Bundle Adjustment?

2 years 3 months ago

Download www.ics.forth.gr

In order to obtain optimal 3D structure and viewing parameter estimates, bundle adjustment is often used as the last step of feature-based structure and motion estimation algorith...

Manolis I. A. Lourakis, Antonis A. Argyros

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status
1	362	Is Levenberg-Marquardt the Most Efficient Optimization Algorithm for Implementing Bundle Adjustment?	claim
2	213	A Robust Algorithm for Point Set Registration Using Mixture of Gaussians
3	155	Probabilistic Boosting-Tree: Learning Discriminative Models for Classification, Recognition, and Clustering	claim
4	146	Modeling Scenes with Local Descriptors and Latent Aspects	claim
5	124	Periodic Motion Detection and Segmentation via Approximate Sequence Alignment	claim
6	119	Local Gabor Binary Pattern Histogram Sequence (LGBPHS): A Novel Non-Statistical Model for Face Representation and Recognition	claim
7	117	Passive Photometric Stereo from Motion	claim
8	111	Prior-Based Segmentation by Projective Registration and Level Sets	claim
9	111	Mutual Information-Based 3D Surface Matching with Applications to Face Recognition and Brain Mapping	claim
10	107	A Spectral Technique for Correspondence Problems Using Pairwise Constraints	claim
11	105	Actions as Space-Time Shapes	claim
12	104	When Does a Camera See Rain?	claim
13	104	Consistent Surface Color for Texturing Large Objects in Outdoor Scenes	claim
14	101	Recovering Human Body Configurations Using Pairwise Constraints between Parts	claim
15	101	Geometric Context from a Single Image	claim
16	98	Parameter-Free Radial Distortion Correction with Centre of Distortion Estimation	claim
17	97	Detecting Rotational Symmetries	claim
18	97	Efficient Learning of Relational Object Class Models	claim
19	95	Creating Efficient Codebooks for Visual Recognition	claim
20	94	Perceptual Scale Space and its Applications	claim
21	87	The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features	claim
22	86	Local Features for Object Class Recognition	claim
23	84	Simultaneous Facial Action Tracking and Expression Recognition Using a Particle Filter	claim
24	82	Bayesian Body Localization Using Mixture of Nonlinear Shape Models	claim
25	81	HMM Based Falling Person Detection Using Both Audio and Video	claim
26	80	Beyond Trees: Common-Factor Models for 2D Human Pose Recovery	claim
27	79	Multi-Modal Tensor Face for Simultaneous Super-Resolution and Recognition	claim
28	78	Behaviour Understanding in Video: A Combined Method	claim
29	78	KALMANSAC: Robust Filtering by Consensus	claim
30	77	Space-Time Scene Manifolds	claim
31	76	An Enhanced Correlation-Based Method for Stereo Correspondence with Sub-Pixel Accuracy	claim
32	75	3D Human Action Recognition Using Spatio-temporal Motion Templates	claim
33	75	Feature Hierarchies for Object Classification	claim
34	71	Building a Classification Cascade for Visual Identification from One Example	claim
35	70	Learning Non-Generative Grammatical Models for Document Analysis	claim
36	69	Object Recognition in High Clutter Images Using Line Features	claim
37	69	Closely Coupled Object Detection and Segmentation	claim
38	68	A Bayesian Approach for Shadow Extraction from a Single Image	claim
39	66	An Algebraic Approach to Surface Reconstruction from Gradient Fields	claim
40	66	3D Object Reconstruction from a Single 2D Line Drawing without Hidden Lines	claim
41	65	3D Shape Recognition and Reconstruction Based on Line Element Geometry	claim
42	65	Progressive Surface Reconstruction from Images Using a Local Prior	claim
43	64	Globally Optimal Solutions for Energy Minimization in Stereo Vision Using Reweighted Belief Propagation	claim
44	64	On the Equivalence of Common Approaches to Lighting Insensitive Recognition	claim
45	64	Patch Based Blind Image Super Resolution	claim
46	63	Class-Specific Material Categorisation	claim
47	63	Sparse Image Coding Using a 3D Non-Negative Tensor Factorization	claim
48	63	Globally Optimal Estimates for Geometric Reconstruction Problems	claim
49	63	Uncalibrated Perspective Reconstruction of Deformable Structures	claim
50	63	A Joint System for Person Tracking and Face Detection	claim
51	62	Inference of Non-Overlapping Camera Network Topology by Measuring Statistical Dependence	claim
52	61	Non-Parametric Self-Calibration	claim
53	61	Vector Boosting for Rotation Invariant Multi-View Face Detection	claim
54	60	A Shape-Based Segmentation Approach: An Improved Technique Using Level Sets	claim
55	59	An Axis-Based Representation for Recognition	claim
56	59	Image Statistics Based on Diffeomorphic Matching	claim
57	59	Priors for People Tracking from Small Training Sets	claim
58	59	A New Framework for Approximate Labeling via Graph Cuts	claim
59	58	Learning Hierarchical Models of Scenes, Objects, and Parts	claim
60	58	Combining Generative Models and Fisher Kernels for Object Recognition	claim
61	57	Guiding Model Search Using Segmentation	claim
62	57	Regular Polygon Detection	claim
63	57	Fundamental Matrix for Cameras with Radial Distortion	claim
64	57	Discontinuity Preserving Stereo with Small Baseline Multi-Flash Illumination	claim
65	56	Efficient Visual Event Detection Using Volumetric Features	claim
66	56	Phase Field Models and Higher-Order Active Contours	claim
67	56	Common Pattern Discovery Using Earth Mover's Distance and Local Flow Maximization	claim
68	55	A Theory of Refractive and Specular 3D Shape by Light-Path Triangulation	claim
69	55	Evaluation of Features Detectors and Descriptors Based on 3D Objects	claim
70	55	Integrated Spatial and Frequency Domain 2D Motion Segmentation and Estimation	claim
71	55	BRDF Invariant Stereo Using Light Transport Constancy	claim
72	55	TemporalBoost for Event Recognition	claim
73	55	Bi-Directional Tracking Using Trajectory Segment Analysis	claim
74	54	Randomized RANSAC with Sequential Probability Ratio Test	claim
75	54	An Ensemble Prior of Image Structure for Cross-Modal Inference	claim
76	54	Vehicle Identification between Non-Overlapping Cameras without Direct Feature Matching	claim
77	54	Mixtures of Dynamic Textures	claim
78	54	Deformation Invariant Image Matching	claim
79	54	An Expectation Maximization Approach to the Synergy between Image Segmentation and Object Categorization	claim
80	54	What Metrics Can Be Approximated by Geo-Cuts, Or Global Optimization of Length/Area and Flux	claim
81	53	Scale-Invariant Contour Completion Using Conditional Random Fields	claim
82	53	Spherical Matching for Temporal Correspondence of Non-Rigid Surfaces	claim
83	53	Multi-View AAM Fitting and Camera Calibration	claim
84	52	Consistent Segmentation for Optical Flow Estimation	claim
85	51	A Supervised Learning Framework for Generic Object Detection in Images	claim
86	51	Surface Parameterization Using Riemann Surface Structure	claim
87	50	Large Deformation Diffeomorphic Metric Mapping of Fiber Orientations	claim
88	50	Tracking Body Parts of Multiple People for Multi-person Multimodal Interface	claim
89	50	Contour-Based Learning for Object Detection	claim
90	50	Shape and Spatially-Varying BRDFs from Photometric Stereo	claim
91	50	Non-Orthogonal Binary Subspace and Its Applications in Computer Vision	claim
92	50	Fast Head Tilt Detection for Human-Computer Interaction	claim
93	50	High Resolution Tracking of Non-Rigid 3D Motion of Densely Sampled Data Using Harmonic Maps	claim
94	50	A Multilevel Banded Graph Cuts Method for Fast Image Segmentation	claim
95	49	Detecting Irregularities in Images and in Video	claim
96	49	Shape Recovery of 3D Data Obtained from a Moving Range Sensor by Using Image Sequences	claim
97	49	Identifying Individuals in Video by Combining "Generative" and Discriminative Head Models	claim
98	49	Learning Object Categories from Google's Image Search	claim
99	49	Fusion of Multi-View Silhouette Cues Using a Space Occupancy Grid	claim
100	49	Layered Active Appearance Models	claim
101	49	LOCUS: Learning Object Classes with Unsupervised Segmentation	claim
102	49	Real-Time Adaptive Hand Motion Recognition Using a Sparse Bayesian Classifier	claim
103	48	Dynamic Refraction Stereo	claim
104	48	Face Recognition in the Presence of Multiple Illumination Sources	claim
105	48	A Stochastic Filter for Fluid Motion Tracking	claim
106	48	Active Search for Real-Time Vision	claim
107	47	A Generative/Discriminative Learning Algorithm for Image Classification	claim
108	47	Shadow Flow: A Recursive Method to Learn Moving Cast Shadows	claim
109	47	Segmentation of Hybrid Motions via Hybrid Quadratic Surface Analysis	claim
110	46	Towards Ultimate Motion Estimation: Combining Highest Accuracy with Real-Time Performance	claim
111	46	A Symmetric Patch-Based Correspondence Model for Occlusion Handling	claim
112	46	Learning Non-Negative Sparse Image Codes by Convex Programming	claim
113	46	Detection of Concentric Circles for Camera Calibration	claim
114	45	Edge-Based Rich Representation for Vehicle Classification	claim
115	45	A Maximum Entropy Framework for Part-Based Texture and Object Recognition	claim
116	45	Structured Light in Scattering Media	claim
117	45	A Graph Cut Algorithm for Generalized Image Deconvolution	claim
118	45	Designing Spatially Coherent Minimizing Flows for Variational Problems Based on Active Contours	claim
119	45	Multimodal Human Computer Interaction: A Survey	claim
120	45	Resolving Hand over Face Occlusion	claim
121	45	Neighborhood Preserving Embedding	claim
122	45	Object Categorization by Learned Universal Visual Dictionary	claim
123	45	Detection, Analysis and Matching of Hair	claim
124	45	Conformal Metrics and True "Gradient Flows" for Curves	claim
125	44	Quasiconvex Optimization for Robust Geometric Reconstruction	claim
126	44	Fast Global Kernel Density Mode Seeking with Application to Localisation and Tracking	claim
127	44	Bottom-up/Top-Down Image Parsing by Attribute Graph Grammar	claim
128	44	A Multi-Scale Hybrid Linear Model for Lossy Image Representation	claim
129	43	Adaptive Enhancement of Cardiac Magnetic Resonance (CMR) Images	claim
130	43	Exploring the Space of a Human Action	claim
131	43	Probabilistic Contour Extraction Using Hierarchical Shape Representation	claim
132	43	Convex Grouping Combining Boundary and Region Information	claim
133	43	Simultaneous Multiple 3D Motion Estimation via Mode Finding on Lie Groups	claim
134	43	Features for Recognition: Viewpoint Invariance for Non-Planar Scenes	claim
135	43	Ensuring Color Consistency across Multiple Cameras	claim
136	43	Eliminating Structure and Intensity Misalignment in Image Stitching	claim
137	43	Automatic 3D Face Modeling from Video	claim
138	43	Appearance Modeling Under Geometric Context	claim
139	42	Real-Time Interactively Distributed Multi-Object Tracking Using a Magnetic-Inertia Potential Model	claim
140	42	Appearance Manifold of Facial Expression	claim
141	42	Realtime IBR with Omnidirectional Crossed-Slits Projection	claim
142	41	A Bilinear Illumination Model for Robust Face Recognition	claim
143	41	Improved Sub-pixel Stereo Correspondences through Symmetric Refinement	claim
144	41	Robust Path-Based Spectral Clustering with Application to Image Segmentation	claim
145	41	Fusing Points and Lines for High Performance Tracking	claim
146	41	On the Spatial Statistics of Optical Flow	claim
147	41	On-Line Density-Based Appearance Modeling for Object Tracking	claim
148	40	Using Eye Reflections for Face Recognition Under Varying Illumination	claim
149	40	Multi-Scale Gesture Recognition from Time-Varying Contours	claim
150	40	Mobile Camera-Based User Interaction	claim
151	40	Can Two Specular Pixels Calibrate Photometric Stereo?	claim
152	40	Photometric Stereo under Perspective Projection	claim
153	39	A Hierarchical Field Framework for Unified Context-Based Classification	claim
154	39	Shape and Appearance Repair for Incomplete Point Surfaces	claim
155	39	Incorporating Visual Knowledge Representation in Stereo Reconstruction	claim
156	39	Mutual Information Regularized Bayesian Framework for Multiple Image Restoration	claim
157	39	Avoiding the "Streetlight Effect": Tracking by Exploring Likelihood Modes	claim
158	39	Incremental Discovery of Object Parts in Video Sequences	claim
159	39	Shape from Symmetry	claim
160	39	Recognizing Human Actions in Videos Acquired by Uncalibrated Moving Cameras	claim
161	38	A Theory of Inverse Light Transport	claim
162	38	A Unifying Approach to Hard and Probabilistic Clustering	claim
163	38	Shapelets Correlated with Surface Normals Produce Surfaces	claim
164	37	Perceptive User Interface, a Generic Approach	claim
165	36	Geometric Invariants and Applications under Catadioptric Camera Model	claim
166	36	Integration of Conditionally Dependent Object Features for Robust Figure/Background Segmentation	claim
167	36	Mesh Optimization Using an Inconsistency Detection Template	claim
168	36	Degenerate Cases and Closed-form Solutions for Camera Calibration with One-Dimensional Objects	claim
169	36	Non-Negative Lighting and Specular Object Recognition	claim
170	36	Reconstructing the Geometry of Flowing Water	claim
171	35	A Study of Detecting Social Interaction with Sensors in a Nursing Home Environment	claim
172	35	Multiple Light Sources and Reflectance Property Estimation Based on a Mixture of Spherical Distributions	claim
173	35	Finding Tree Structures by Grouping Symmetries	claim
174	35	Visual Learning Given Sparse Data of Unknown Complexity	claim
175	35	Dynamic Measurement Clustering to Aid Real Time Tracking	claim
176	35	Robust Point Matching for Two-Dimensional Nonrigid Shapes	claim
177	34	Good Continuation of General 2D Visual Features: Dual Harmonic Models and Computational Inference	claim
178	34	A Model-Based Vehicle Segmentation Method for Tracking	claim
179	34	More-Than-Topology-Preserving Flows for Active Contours and Polygons	claim
180	34	Learning the Probability of Correspondences without Ground Truth	claim
181	33	Fast Texture-Based Tracking and Delineation Using Texture Entropy	claim
182	33	Using Extended Light Sources for Modeling Object Appearance under Varying Illumination	claim
183	32	An Integrated Framework for Image Segmentation and Perceptual Grouping	claim
184	32	How Hard is 3-View Triangulation Really?	claim
185	32	Image Based Regression Using Boosting Method	claim
186	31	On Optimal Light Configurations in Photometric Stereo	claim
187	29	Visual Speech Recognition with Loosely Synchronized Feature Streams	claim
188	28	Learning Effective Image Metrics from Few Pairwise Examples	claim
189	28	Integrating the Effects of Motion, Illumination and Structure in Video Sequences	claim
190	28	Fixed Point Probability Field for Complex Occlusion Handling	claim
191	28	Learning Models for Predicting Recognition Performance	claim
192	27	Object Detection in Aerial Imagery Based on Enhanced Semi-Supervised Learning	claim
193	26	Vignette and Exposure Calibration and Compensation	claim
194	24	Separating Transparent Layers of Repetitive Dynamic Behaviors	claim
195	22	Registration of Multimodal Fluorescein Images Sequence of the Retina	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers