A layered approach to stereo reconstruction

Simon Baker; Richard Szeliski; P. Anandan

doi:10.1109/cvpr.1998.698642

Abstract

We propose a framework for extracting structure from stereo which represents the scene as a collection of approximately planar layers. Each layer consists of an explicit 3D plane equation, a colored image with per-pixel opacity (a sprite), and a per-pixel depth offset relative to the plane. Initial estimates of the layers are recovered using techniques taken from parametric motion estimation. These initial estimates are then refined using a re-synthesis algorithm which takes into account both occlusions and mixed pixels. Reasoning about such effects allows the recovery of depth and color information with high accuracy even in partially occluded regions. Another important benefit of our framework is that the output consists of a collection of approximately planar regions, a representation which is far more appropriate than a dense depth map for many applications such as rendering and video parsing.

Keywords

PixelComputer visionArtificial intelligenceRendering (computer graphics)Computer scienceOffset (computer science)PlanarDepth mapImage-based modeling and renderingStereo displayReal-time renderingParametric statisticsParametric equationComputer graphics (images)MathematicsImage (mathematics)Geometry

Affiliated Institutions

Related Publications

Motion segmentation with occlusions on the superpixel graph

Alper Ayvacı , Stefano Soatto

We present a motion segmentation algorithm that partitions the image plane into disjoint regions based on their parametric motion. It relies on a finer partitioning of the image...

2009 33 citations

Super-resolution via Transform-Invariant Group-Sparse Regularization

Carlos Fernandez‐Granda , Emmanuel J. Candès

We present a framework to super-resolve planar regions found in urban scenes and other man-made environments by taking into account their 3D geometry. Such regions have highly s...

2013 56 citations

Super-Resolution Without Explicit Subpixel Motion Estimation

Hiroyuki Takeda , Peyman Milanfar , Matan Protter +1 more

The need for precise (subpixel accuracy) motion estimates in conventional super-resolution has limited its applicability to only video sequences with relatively simple motions s...

2009 IEEE Transactions on Image Processing 301 citations

Example-based super-resolution

William T. Freeman , Thouis R. Jones , Egon Pasztor

We call methods for achieving high-resolution enlargements of pixel-based images super-resolution algorithms. Many applications in graphics or image processing could benefit fro...

2002 IEEE Computer Graphics and Applications 2502 citations

Robust Wide Baseline Stereo from Maximally Stable Extremal Regions

Jiřı́ Matas , Ondřej Chum , M. Urban +1 more

Abstract The wide-baseline stereo problem, i.e. the problem of establishing correspondences between a pair of images taken from different viewpoints is studied. A new set of ...

2002 1345 citations

Publication Info

Year: 2002
Type: article
Pages: 434-441
Citations: 177
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

A layered approach to stereo reconstruction

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

177

OpenAlex

Cite This

APA Style

                            
                                    Simon Baker, 
                                
                                    Richard Szeliski, 
                                
                                    P. Anandan
                                
                            (2002). 
                            A layered approach to stereo reconstruction. 
                            
                            , 434-441.
                            https://doi.org/10.1109/cvpr.1998.698642

Identifiers

DOI: 10.1109/cvpr.1998.698642