Parameterized Variety Based View Synthesis Scheme for Multi-view 3DTV

Sharma, Mansi; Chaudhury, Santanu; Lall, Brejesh

doi:10.1007/978-3-642-37447-0_41

Cited by 5 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A consistent new linear simplified solution of the FP-PIV approach [2] that avoids redundant inconsistencies and yield physically-valid perspective 3D views. Fig.…”

Section: )mentioning

confidence: 99%

“…The values of p , q , x , y , z are nonzero but (a priori) unknown. For parameterizing the scene, these world points Q0, Q1, Q2, Q are projected under the full perspective camera model [2]. The Euclidean constraints associated with the full perspective cameras are explicitly imposed to yield a system of multi-variate quadratic equations [2].…”

Section: )mentioning

confidence: 99%

“…The basic concept of parameterized image variety (or PIV) was proposed earlier by Genc and Ponce [1] for image-based characterization of the structure of all possible views of a scene, observed under weak or paraperspective camera models. A generalized PIV approach for handling full perspective cameras, termed as full perspective PIV (or FP-PIV), is recently developed by Sharma et al [2]. Their algorithm efficiently constructs minimal parameterization of the 3D space by reducing the set of perspective camera views of a scene to a sixdimensional variety (i.e.…”

Section: Introductionmentioning

confidence: 99%

“…The proposed Kinect-variety framework overcomes these issues and efficiently deals with the redundancy of parameterized space. Our hybrid technique, in fact, presents an alternate formulation to solve this formidable full-perspective variety problem of elimination theory [1], [2]. The major novel algorithmic contributions of this paper are:…”

Section: Introductionmentioning

confidence: 99%

“…a subspace defined by multi-variate quadratic polynomials). The algebraic formulation presented in [2] addresses the problem of directly inferring new photorealistic views of a scene from arbitrary viewpoints as an instances of this explicitly constructed parameterized space. The advantage of their method is that it does not make use of any 3D model of the scene and predict novel views from existing few sample images captured from uncalibrated cameras.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Kinect-Variety Fusion: A Novel Hybrid Approach for Artifacts-Free 3DTV Content Generation

Sharma

Chaudhury

Lall

2014

2014 22nd International Conference on Pattern Recognition

Self Cite

View full text Add to dashboard Cite

This paper presents a novel low-cost hybrid Kinect-variety based content generation scheme for 3DTV displays. The integrated framework constructs an efficient consistent image-space parameterization of 3D scene structure using only sparse depth information of few reference scene points. Under full-perspective camera model, the enforced Euclidean constraints simplify the synthesis of high quality novel multiview content for distinct camera motions. The algorithm does not rely on complete precise scene geometry information, and are unaffected by scene complex geometric properties, unconstrained environmental variations and illumination conditions. It, therefore, performs fairly well under a wider set of operation condition where the 3D range sensors fail or reliability of depth-based algorithms are suspect. The robust integration of vision algorithm and visual sensing scheme complement each other's shortcomings. It opens new opportunities for envisioning vision-sensing applications in uncontrolled environments. We demonstrate that proposed robust integration provides guarantees on the completeness and consistency of the algorithm. This leads to improved reliability on an extensive set of experimental results.

show abstract

“…A consistent new linear simplified solution of the FP-PIV approach [2] that avoids redundant inconsistencies and yield physically-valid perspective 3D views. Fig.…”

Section: )mentioning

confidence: 99%

Section: )mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations