Metric 3D reconstruction and texture acquisition of surfaces of revolution from a single uncalibrated view

@article{Colombo2005Metric3R,
  title={Metric 3D reconstruction and texture acquisition of surfaces of revolution from a single uncalibrated view},
  author={Carlo Colombo and A. Bimbo and Federico Pernici},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2005},
  volume={27},
  pages={99-114}
}
Image analysis and computer vision can be effectively employed to recover the three-dimensional structure of imaged objects, together with their surface properties. In this paper, we address the problem of metric reconstruction and texture acquisition from a single uncalibrated view of a surface of revolution (SOR). Geometric constraints induced in the image by the symmetry properties of the SOR structure are exploited to perform self-calibration of a natural camera, 3D metric reconstruction… 
View on IEEE
dsi.unifi.it
118 Citations
Highly Influential Citations
7
Background Citations
48
Methods Citations
26

118 Citations

Camera Calibration with Two Arbitrary Coaxial Circles
TLDR
Experimental results show that the approach for camera calibration from the image of at least two circles arranged in a coaxial way is accurate enough for several vision applications, encompassing 3D realistic model acquisition from single images, and desktop 3D object scanning.
589 Reconstruction of 3 D Geometry of General Curved Surfaces from a Single Image
Construction of 3D model from 2D images is important in reverse engineering and inspection applications. This work presents a new method to construct the 3D model of a free-form surface from a single…
Linear, Discrete, and Quadratic Constraints in Single-image 3D Reconstruction
In this thesis, we investigate the formulation, optimization and ambiguities in single-image 3D surface reconstruction from geometric and photometric constraints. We examine linear, discrete and…
Reconstructing Symmetric Curved Surfaces from a Single Image and Its Application
TLDR
This work demonstrates that the horizontally flipped image of the reflective symmetric objects is equivalent to an image photographed from another position under the simplified perspective projection, so the traditional structure from motion techniques can be used to recover the 3D feature points on them.
A Review of Geometry Recovery from a Single Image Focusing on Curved Object Reconstruction
TLDR
This chapter examines a representative set of state-of-the-art reconstruction approaches, which are applicable to real-world images, and classify the approaches according to their reconstruction objective and compare them based on a variety of important criteria.
Image Mosaicing from Uncalibrated Views of a Surface of Revolution
TLDR
A novel approach to obtain a mosaic image for the texture content of a surface of revolution (SOR) from a collection of uncalibrated views using the SOR scene constraint to calibrate each view and extracting the corresponding pictorial content into a global representation.
Refining Single View Calibration With the Aid of Metric Scene Properties
TLDR
The proposed method refines the former by numerically minimizing an error term corresponding to the discrepancy between the scene’s known metric properties and the values measured with the aid of the calibration estimate.
Precise 3D Reconstruction from a Single Image
TLDR
A novel method which uses a set of auxiliary reference grids to precisely reconstruct 3D objects from a single uncalibrated image and has the ability of handling complex polyhedral objects and curved surfaces within one framework is proposed.
Relative Volume Constraints for Single View 3D Reconstruction
TLDR
The concept of relative volume constraints is introduced in order to account for insufficient information in the reconstruction of 3D objects from a single image and a convex relaxation of the constrained optimization problem is proposed which can be solved optimally in a few seconds on graphics hardware.
Absolute Pose and Structure from Motion for Surfaces of Revolution: Minimal Problems Using Apparent Contours
TLDR
Assuming apparent contours as input that have been identified and segmented with reasonable accuracy, the minimal problems are demonstrated to produce accurate SoR pose and shape results when used as part of a RANSAC-based hypothesis generation and evaluation pipeline.
...
...

References

SHOWING 1-10 OF 71 REFERENCES
Reconstruction of surfaces of revolution from single uncalibrated views
Uncalibrated 3D metric reconstruction and flattened texture acquisition from a single view of a surface of revolution
  • C. ColomboA. BimboF. Pernici
  • Computer Science
    Proceedings. First International Symposium on 3D Data Processing Visualization and Transmission
  • 2002
TLDR
A geometric approach for reconstructing 3D textured graphical models of surface of revolution (SOR) objects from a single uncalibrated view that is quite simple, yet accurate and robust; its applications range from the preservation, analysis and classification of cultural heritage, to advanced graphics and multimedia.
Camera Calibration from Surfaces of Revolution
TLDR
It is shown that two images of a surface of revolution will provide enough information for determining the aspect ratio, focal length, and principal point of a camera with fixed intrinsic parameters.
Camera Calibration from Symmetry
TLDR
It is shown that 2 images of surface of revolution will provide enough information for determining the aspect ratio, focal length and principal point of a camera, and an analytical error model is developed.
Single Axis Geometry by Fitting Conics
TLDR
A new approach for recovering 3D geometry from an uncalibrated image sequence of a single axis (turntable) motion based on fitting a conic locus to corresponding image points over multiple views is described.
Epipolar geometry from profiles under circular motion
TLDR
This work addresses the problem of motion estimation from profiles (apparent contours) of an object rotating on a turntable in front of a single camera with a practical and accurate technique that is precise enough to reconstruct the shape of the object.
Metric rectification for perspective images of planes
  • D. LiebowitzAndrew Zisserman
  • Mathematics
    Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)
  • 1998
TLDR
The novel contributions are that in a stratified context the various forms of providing metric information can be represented as circular constraints on the parameters of an affine transformation of the plane, providing a simple and uniform framework for integrating constraints.
Repeated Structures: Image Correspondence Constraints and 3D Structure Recovery
TLDR
The development of feature correspondence relations based on the epipolar geometry induced in the image by the repeated structure is developed, and in some cases, correspondence is based on projective homologies rather than a true ep bipolar geometry.
Projection distortion analysis for flattened image mosaicing from straight uniform generalized cylinders
Automatic 3D Model Construction for Turn-Table Sequences
TLDR
A system which, given a sequence of images of an object rotating about a single axis, generates a textured 3D model fully automatically, and requires no prior information about the cameras or scene, and does not require that the turntable angles be known.
...
...