Image-based rendering using image-based priors

Fitzgibbon,; Wexler, Lisa; Zisserman,

doi:10.1109/iccv.2003.1238625

Cited by 140 publications

(73 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We first verified our viewpoint specification method by showing a simulated free viewpoint moving path by using data that is made available on the Internet by the authors of [1] since the cameras are calibrated and the associated path has Euclidian meaning in real world. Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Note that in this case, potentially one can use either of the methods described in [1] and [6]. However, as discussed previously, these methods are not practical to use (e.g., it is unlikely that we can ask a TV viewer to input a rotation matrix and a translation vector).…”

Section: Viewpoint Interpolation: Calibrated Casementioning

confidence: 99%

“…This problem is also known as image-based rendering (IBR), which has been extensively studied in the literature. For example, [10] and [11] are among the early papers, and more recent ones include [1,3,6,12,14]. While there exist alternative approaches to virtual view synthesis in FTV (e.g., the ray-space sampling and interpolation approach in [9]), IBR has the potential of requiring fewer cameras and loose constraints on the camera configuration.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Virtual View Specification and Synthesis in Free Viewpoint Television Application

Zhou

et al. 2006

Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06)

View full text Add to dashboard Cite

In conventional TV, users can get only a single view of a real 3D world. The view is determined not by a user but by the camera position during acquisition. Free viewpoint television (FTV) is a new concept which aims at giving viewers the flexibility to select a novel viewpoint by employing multiple video streams as the input. Current proposed solutions for FTV include those based on ray-space sampling and interpolation. Most existing work makes the assumption that the cameras are calibrated. Moreover, virtual view specification is done in ways that would not be practical for actual use (e.g., some methods specify the virtual view by a rotation matrix and a translation vector). This paper proposes a framework for FTV based on image-based rendering, complete with key algorithmsfor color-based segmentation and correspondence, and multiple-image-based virtual view synthesis from uncalibrated cameras. Moreover, we propose an intuitive approach to specifying the virtual viewpoint, based on any two views chosen by the user. This makes the specification of the virtual view very intuitive and thus practical for the FTV application. Experiments with real video streams were performed to validate the proposed approaches.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Viewpoint Interpolation: Calibrated Casementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Virtual View Specification and Synthesis in Free Viewpoint Television Application

Zhou

et al. 2006

Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06)

View full text Add to dashboard Cite

show abstract

“…(1) was already used in [11] for successfully resolving ambiguities which are otherwise inherent to the geometric problem of new-view synthesis from multiple camera views. The objective function of [11] was defined on 2D images. Their local distance between 2D patches was based on SSD of color information and included geometric constraints.…”

Section: The Optimizationmentioning

confidence: 99%

Space-time video completion

Wexler

Shechtman

Irani

Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.

454

590

View full text Add to dashboard Cite

We present a method for space-time completion of large space-time "holes" in video sequences of complex dynamic scenes. The missing portions are filled-in by sampling spatio-temporal patches from the available parts of the video, while enforcing global spatio-temporal consistency between all patches in and around the hole. This is obtained by posing the task of video completion and synthesis as a global optimization problem with a well-defined objective function. The consistent completion of static scene parts simultaneously with dynamic behaviors leads to realistic looking video sequences.Space-time video completion is useful for a variety of tasks, including, but not limited to: (i) Sophisticated video removal (of undesired static or dynamic objects) by completing the appropriate static or dynamic background information, (ii) Correction of missing/corrupted video frames in old movies, and (iii) Synthesis of new video frames to add a visual story, modify it, or generate a new one. Some examples of these are shown in the paper.

show abstract

“…Fitzgibbon et al [8] use robust kernels for the photo consistency test and implicitly solve visibility problem in this manner. For each pixel in a desired virtual camera view, statistics are gathered for the corresponding rays through the reference images in order to determine the appropriate color.…”

Section: Introductionmentioning

confidence: 99%

A New Photo Consistency Test for Voxel Coloring

Yin

Cooperstock

The 2nd Canadian Conference on Computer and Robot Vision (CRV'05)

View full text Add to dashboard Cite

Volumetric scene reconstruction is an important task for many vision applications. Most voxel coloring or space carving techniques required for this purpose suffer from the coupled problems of visibility and photo consistency. We propose a new photo consistency measurement that implicitly solves the visibility problem, thus permitting an efficient, single-scan voxel inspection that can be parallelized.

show abstract

Image-based rendering using image-based priors

Cited by 140 publications

References 20 publications

Virtual View Specification and Synthesis in Free Viewpoint Television Application

Virtual View Specification and Synthesis in Free Viewpoint Television Application

Space-time video completion

A New Photo Consistency Test for Voxel Coloring

Contact Info

Product

Resources

About