A stereoscopic video conversion scheme based on spatio-temporal analysis of MPEG videos

IEEE Trans. on Broadcast.

Chen

Kuo

et al. 2014

In this paper, a computing framework for adaptivesupport-window-based multi-lateral filters is proposed. The socalled multi-lateral filters, extended from the well-known bilateral filter, have found their broaden applications in noise/highfrequency suppression for 2-D image and 3-D depth processing. Our filters rely on binarizing the traditional pixel-wise weights to be only 0 or 1, resulting in an adaptive support window whose shape depends on the local image structure of the central anchor pixel. A cross-subwindow-based algorithm is devised to compute the adaptive support window. A fast algorithm based on integral images is also devised for data aggregation within such an irregularly shaped support window. Taking advantage of the integral images, our scheme presents a near constanttime complexity regardless of the size and shape of the support window. Experiments show that both noise suppression and edge-preserving can be simultaneously achieved by using our proposed framework. The average speedup ratios of our scheme are 14X∼49X and 1.3X∼5.6X against the traditional and the O(1) implementations, respectively. Our scheme also has the advantage of easy extension to tri-lateral and quadri-lateral filters, whereas other O(1) algorithms might not.Index Terms-Bilateral filter, adaptive support window, data aggregation, integral image, depth image processing

Section: B Quadri-lateral Filter [8]mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

A Computing Framework of Adaptive Support-Window Multi-Lateral Filter for Image and Depth Processing

IEEE Trans. on Broadcast.

Chen

Kuo

et al. 2014

“…The FAM is composed of facial regions detected by using face detector [21]. Except for facial cue, we linearly combine the other visual clues and then yield a non-facial attention map (NFAM) [17]. For the t-th frame, its NFAM can be expressed as follows:…”

Section: B4 Facial Cue Combinationmentioning

confidence: 99%

Video quality enhancement based on visual attention model and multi-level exposure correction

2015

Multimed Tools Appl

Self Cite

Due to unfavorable environmental conditions such as lack of lighting, poor visual quality in images and videos may make intelligent image/video systems unstable. This means that visual quality enhancement plays an important role in image/video processing, computer vision, and pattern recognition. In this paper, we propose a video quality enhancement scheme based on visual attention model and multi-level exposure correction. To this end, the proposed scheme is composed of four parts: pre-processing, visual attention model generation, multi-level exposure correction, and temporal filtering. To extract more visual cues for visual attention model generation, a pre-processing is used to modify each frame. After preprocessing, facial and non-facial cues are measured to generate visual attention maps of each frame. On the basis of visual attention maps, a multi-level exposure correction algorithm is utilized to adjust the exposure level of each frame and then create several intermediate results. After fusing intermediate results, a synthesized image with good visual quality can be obtained. To avoid flicker effect, a temporal filter is exploited to make the variance of the exposure level small in the temporal domain. To evaluate the performance of the proposed scheme, some images/videos captured by mobile phones and digital cameras are tested. The experimental results show that the proposed scheme can effectively deal with the images/videos with low and high exposure levels. The results also demonstrate that the proposed scheme outperforms some existing methods in terms of visual quality.

“…Traditional 3D video format in terms of stereo-view sequence is only suitable for glassed 3D display. To provide more realistic 3D perception (e.g., auto-stereoscopic display [1][2]), the format of video-plusdepth is preferable and gains much attention recently. Thanks to the DIBR (Depth-Image-Based Rendering) technique that is capable of combining color and depth information [1][2] for the synthesis of multiple novel-views (so that observes can see objects from multiple viewing directions).…”

Section: Introductionmentioning

confidence: 99%

Sprite generation for hole filling in depth image-based rendering

2014 IEEE International Conference on Image Processing (ICIP)

Hsieh

Lie

2014

Self Cite

In this paper, we propose a new depth image-based rending (DIBR) scheme for 3DTV applications, which is based on temporal hole filling with sprite generation. Dissimilar to traditional methods (e.g., spatial interpolation and inpainting), temporal information is utilized to recover the holes with true background information. The proposed scheme is composed of two parts: sprite generation and virtual view synthesis. To collect sufficiently temporal information, a key-frame-based sprite generation algorithm was developed to incrementally and accurately fuse the background color and depth information from successive frames. Then the holes in the synthesized virtual view can be recovered by referring to the constructed sprite models. Experiments demonstrate that our proposed scheme is capable of achieving good results and outperforms some existing methods subjectively and objectively.