An adaptive interpolation scheme for 2-D mesh motion compensation

Hsu, Pai-Hui; Liu, K.J.R.; Chen, T.

doi:10.1109/icip.1997.632204

Cited by 4 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Altunbaşak et al [25] proposed an occlusion adaptive mesh tracking method for frame-based video compression, where motion-model failure regions were identified at each frame, and the texture in these regions were incrementally coded to reconstruct the next frame. Recently, an interpolative frame based 2-D mesh motion compensation method is proposed to handle occlusion and motion discontinuity problems [26]. In this paper we address synthesis of a single object mosaic in the presence of mildly deformable object motion, and transfiguration of video objects with occlusion using this mosaic representation.…”

Section: Introductionmentioning

confidence: 99%

Two-dimensional mesh-based mosaic representation for manipulation of video objects with occlusion

Toklu

Erdem

Tekalp

2000

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

We present a two-dimensional (2-D) mesh-based mosaic representation, consisting of an object mesh and a mosaic mesh for each frame and a final mosaic image, for video objects with mildly deformable motion in the presence of self and/or object-to-object (external) occlusion. Unlike classical mosaic representations where successive frames are registered using global motion models, we map the uncovered regions in the successive frames onto the mosaic reference frame using local affine models, i.e., those of the neighboring mesh patches. The proposed method to compute this mosaic representation is tightly coupled with an occlusion adaptive 2-D mesh tracking procedure, which consist of propagating the object mesh frame to frame, and updating of both object and mosaic meshes to optimize texture mapping from the mosaic to each instance of the object. The proposed representation has been applied to video object rendering and editing, including self transfiguration, synthetic transfiguration, and 2-D augmented reality in the presence of self and/or external occlusion. We also provide an algorithm to determine the minimum number of still views needed to reconstruct a replacement mosaic which is needed for synthetic transfiguration. Experimental results are provided to demonstrate both the 2-D mesh-based mosaic synthesis and two different video object editing applications on real video sequences.

show abstract

Section: Introductionmentioning

confidence: 99%

Two-dimensional mesh-based mosaic representation for manipulation of video objects with occlusion

Toklu

Erdem

Tekalp

2000

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…An exception is the paper [9], which uses a bank of interpolation filters to provide flexibility in billinear motion interpolation. A different adaptive approach consists of switching locally between a global and a local motion compensation model [10], [11].…”

Section: Introductionmentioning

confidence: 99%

On spatial adaptation of motion-field smoothness in video coding

Ishwar

Moulin

2000

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Most motion-compensation methods dealt with in the literature make strong assumptions about the smoothness of the underlying motion field. For instance, block-matching algorithms assume a blockwise-constant motion field and are adequate for translational motion models; control-grid interpolation assumes a blockwise bilinear motion field and captures zooming and warping fairly well. Time-varying imagery, however, often contains both types of motion (as well as others), and hence exhibits a high degree of spatial variability of its motion-field smoothness properties. We develop a simple method to spatially adapt the smoothness of the motion field. The proposed method demonstrates substantial improvements in video quality over a wide range of bit rates. To this end, we introduce the notion of a motion field that is characterized by a set of labels. The labels provide the flexibility to adaptively switch between two different motion models locally. The individual motion models have very different smoothness properties. The switched framework for motion compensation performs significantly better than each of its constituent motion models, in terms of both visual quality and signal-to-noise ratio (0.3-0.7 dB on the average). Finally, we develop an extension of this method that enhances the overlapped block motion compensation scheme by allowing spatial adaptation of the window function.

show abstract

“…Several contribution have been made about this problem. In [Nie95], is switched between bilinear and nearest neighbour interpolation in case of high variation of the motion vectors of a rectangle, in [Hsu97,HsuOl], the authors presentad a method of adaptive interpolation with a set of predefined interpolation patterns and in different contributions [Ish97, Hei98, Mar99b] has been found the proposal of a switching between BMA and CGI. Altunbasak et al [Alt97c] presented a method where the mesh is split and redesigned in regions of uncovered background (UB) and no node points can exist in regions of background to be covered (BTBC), but already for the detection of UB and BTBC a series of costly calculations as DFD and MF estimation have to be performed.…”

Section: Treatment Of Discontinuities By Mesh Deformationsmentioning

confidence: 99%

Compensación de movimiento avanzada para codificación de vídeo

Eckert¹

View full text Add to dashboard Cite

En primer lugar quiero dar las gracias a toda la gente del GTI, que me han acogido con mucho cariño, con el resultado que volví y volví otra vez para quedarme... ¿Os habréis arrepentido? ;-) Gracias en especial a Narciso, por su ayuda con las formalidades, becas, escritos, etc. y sobre todo por los viajes, lo que más disfruté durante estos años. Gracias también a Luis, por los ánimos que me ha dado siempre con su manera tan abierta y alegre, y a Fernando y Nacho, mis tutores. Nacho me facilitó empezar esta tesis, aunque ya le di la lata los dos años anteriores. Y sin Perdi mis informes hubieran sido ilegibles ¡Gracias por tu paciencia infinita! Sehr viel Rückenstárkung habe ich auch von meinen lieben Deutschen erhalten. An allererster Stelle steht natürlich meine liebe Mami, die mich, schweren Herzens, aber doch immer viel Mut machend, so weit hat weggehen lassen. Danke auch für all die Jahre meines Studiums in denen Du mir bei Seite gestanden hast! Danken mochte ich auch alien meinen Freunden, die mich nie vergessen haben und die mich immer wie zu Hause fühlen lassen, wenn wir uns denn alie Ewigkeiten einmal sehen. Speziell Helge, der wie ein grosser Bruder ist, und Natascha mit der ich so schnell so feste Bande knüpfen konnte. Vor allem aber an Clemens, der beste Zuhorer und Ratgeber auf Distanz, den ich mir vorstellen kann! Ganz dolí Danke auch an meinen süssen kleinen Spatz, der mir so das Leben bereichert hat, y sobre todo a mi chiqui, que me acogió del bosque, que me envuelve su amor en lubina a la sal, que me escucha con paciencia y me hace reír. En fin ¡qué me hace más feliz que nunca! 4 Creación de regiones A continuación se describe como se obtienen las regiones de error alto o de color de piel. Este proceso se denomina procesamiento region-in-frame based (basado en regiones del cuadro) para distinguirlo del procesamiento frame-based (basado en el cuadro entero) o del object-based (basado en objetos).Las regiones creadas se forman exclusivamente a partir de la imagen de error de predicción, con lo cual, según el criterio de selección, no tienen necesariamente relación con el contenido de la imagen.

show abstract

An adaptive interpolation scheme for 2-D mesh motion compensation

Cited by 4 publications

References 8 publications

Two-dimensional mesh-based mosaic representation for manipulation of video objects with occlusion

Two-dimensional mesh-based mosaic representation for manipulation of video objects with occlusion

On spatial adaptation of motion-field smoothness in video coding

Compensación de movimiento avanzada para codificación de vídeo

Contact Info

Product

Resources

About