Corpus ID: 11270576

Monocular Extraction of 2.1D Sketch

@inproceedings{Amer2010MonocularEO,
  title={Monocular Extraction of 2.1D Sketch},
  author={Mohamed R. Amer and Raviv Raich and Sinisa Todorovic},
  booktitle={ICIP},
  year={2010}
}
The 2.1D sketch is a layered representation of occluding and occluded surfaces of the scene. Extracting the 2.1D sketch from a single image is a difficult and important problem arising in many applications. We present a fast and robust algorithm that uses boundaries of image regions and T-junctions, as important visual cues about the scene structure, to estimate the scene layers. The estimation is a quadratic optimization with hinge-loss based constraints, so the 2.1D sketch is smooth in all… Expand
Monocular Extraction of 2.1D Sketch Using Constrained Convex Optimization
TLDR
The new optimization transfer algorithm admits a closed-form expression of the duality gap, and thus allows explicit computation of the achieved accuracy, and is efficient with quadratic complexity in the number of constraints between image regions. Expand
A global energy optimization framework for 2.1D sketch extraction from monocular images
TLDR
A global optimization framework for inferring the 2.1D sketch from a monocular image using a global energy optimization framework and a hybrid evolution algorithm is utilized to minimize the global energy function efficiently. Expand
Occlusions and Their Role in Object Detection in Video
TLDR
The problem of object detection in a video can be cast as an unsupervised segmentation scheme using occlusion cues and solved using convex optimization for an unknown number and geometry of objects in the scene. Expand
Detachable Object Detection: Segmentation and Depth Ordering from Short-Baseline Video
TLDR
An approach for segmenting a moving image into regions that correspond to surfaces in the scene that are partially surrounded by the medium is described and an entirely unsupervised scheme to detect and segment an arbitrary and unknown number of objects is described. Expand
Hallucinating Stereoscopy from a Single Image
TLDR
A novel method for enabling stereoscopic viewing of a scene from a single pre‐segmented image using a rough approximation of the scene's 3D model using a number of simple depth and occlusion cues and shape priors is introduced. Expand
Multiview Conversion of 2 D Cartoon Images
Multiview images offer great potential for immersive autostereoscopic displays due to the multiple perspectives of a dynamic 3D scene that can be simultaneously presented to a viewer. Traditional 2DExpand
Depth from a Single Image Through User Interaction
TLDR
This paper presents a method to obtain a depth map from a single image of a scene by exploiting both image content and user interaction as an optimization process across a graph. Expand
DepthCut: improved depth edge estimation using multiple unreliable channels
TLDR
This paper proposes DepthCut, a data-driven fusion of the channels using a convolutional neural network trained on a large dataset with known depth, and demonstrates that the depth edges result in superior segmentation and depth orderings. Expand
Recovering Relative Depth from Low-Level Features Without Explicit T-junction Detection and Interpretation
This work presents a novel computational model for relative depth order estimation from a single image based on low-level local features that encode perceptual depth cues such as convexity/concavity,Expand
A model of figure ground organization incorporating local and global cues
TLDR
A biologically motivated, feed forward computational model of FGO incorporating convexity, surroundedness, parallelism as global cues and Spectral Anisotropy (SA), T-junctions as local cues is presented, indicating SA and T-Junctions are not mutually contradictory. Expand
...
1
2
...

References

SHOWING 1-10 OF 12 REFERENCES
The 2.1-D sketch
TLDR
A model is described for image segmentation that tries to capture the low-level depth reconstruction exhibited in early human vision, giving an important role to edge terminations, which gives rise to a family of optimal contours, called nonlinear splines, that minimize length and the square of curvature. Expand
Recovering Occlusion Boundaries from a Single Image
TLDR
The goal is to recover the occlusion boundaries and depth ordering of free-standing structures in the scene using the traditional edge and region cues together with 3D surface and depth cues. Expand
Automatic photo pop-up
This paper presents a fully automatic method for creating a 3D model from a single photograph. The model is made up of several texture-mapped planar billboards and has the complexity of a typicalExpand
Hierarchical region-based representation for segmentation and filtering with depth in single images
TLDR
An algorithm for tree-based representation of single images and its applications to segmentation and filtering with depth is presented and a depth-oriented filter is proposed, which allows to remove foreground regions and to replace them with a plausible background. Expand
Cooperative Robust Estimation Using Layers of Support
TLDR
A multilayer estimation framework which uses support maps to represent the segmentation of the image into homogeneous chunks, which can represent objects that are split into disjoint regions, or have surfaces that are transparently interleaved. Expand
Monocular Depth by Nonlinear Diffusion
TLDR
This paper proposes a mathematical and computational translation of gestalt depth perception theory, from the detection of local depth cues to their synthesis into a consistent global depth perception. Expand
Bayesian Inference for Layer Representation with Mixed Markov Random Field
TLDR
This paper presents a Bayesian inference algorithm for image layer representation [26], 2.1D sketch [6], with mixed Markov random field, based on Swendsen-Wang Cut algorithm and satisfactory results are shown in the experiments. Expand
Layered representations for vision and video
  • E. Adelson
  • Computer Science
  • Proceedings IEEE Workshop on Representation of Visual Scenes (In Conjunction with ICCV'95)
  • 1995
TLDR
This work is developing systems that decompose image sequences into overlapping layers, rather like the "cels" used by a traditional animator, which can achieve greatly improved motion analysis and image segmentation and achieve frame-rate independence as a side benefit. Expand
A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
TLDR
A database containing 'ground truth' segmentations produced by humans for images of a wide variety of natural scenes is presented and an error measure is defined which quantifies the consistency between segmentations of differing granularities. Expand
Accelerated Landweber iterations for the solution of ill-posed equations
SummaryIn this paper, the potentials of so-calledlinear semiiterative methods are considered for the approximate solution of linear ill-posed problems and ill conditioned matrix equations. SeveralExpand
...
1
2
...