View synthesis with depth information based on graph cuts for FTV

Tran, Anh Tu; Harada, Kaoru

doi:10.1109/fcv.2013.6485507

Cited by 5 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Table III, compared with current techniques, the proposed solution provides average PSNR gains of 2.6 and 1.4 dB for the Ballet and Breakdancers sequences, respectively, and comparable SSIM values with [28] and [32]. This gain is achieved due to the use of depth information in all rendering steps, namely, depth boundary detection, brightness adjustment, and inpainting.…”

Section: A Objective Evaluation Of the Dibr Algorithmsupporting

confidence: 54%

“…The warped depth maps are median filtered, and the modified pixels are inverse warped to close the narrow holes. This reduces the amount of warping operations by almost 50% compared with other algorithms, which inverse warp all pixels of the filtered depth map [30]- [32]. The procedure is visualized in Fig.…”

Section: Design Of the Dibr Algorithmmentioning

confidence: 98%

“…These include depth preprocessing [27], illumination compensation [28], ghost contours avoidance [29], and depth postprocessing using bilateral filters [30]. In [32], pixel classification, graph cuts, and depth-based inpainting are used to refine the virtual view. In [33], a symmetric bidirectional expansion algorithm and corresponding blending function are proposed to remove ghosting artifacts.…”

Section: Dibrmentioning

confidence: 99%

See 2 more Smart Citations

Broadcasting Free-Viewpoint Television Over Long-Term Evolution Networks

Zarb

Debono

2016

IEEE Systems Journal

View full text Add to dashboard Cite

Recent advances in mobile device technology, cellular networks, and multimedia coding have paved the way for a wide range of innovative multimedia services that can be delivered to mobile users. An interesting application is free-viewpoint television (FTV), which allows the viewer to interactively select the scene viewing angle. Conveying this service over cellular networks is very challenging due to the large bandwidth requirements and limitations in computational power, memory, and battery resources on mobile terminals. Moreover, providing FTV over mobile systems necessitates new means for quality evaluation, which consider cellular network parameters. To address these challenges, we propose a scalable FTV broadcast architecture for long-term evolution cellular networks. To alleviate complex processing on mobile receivers, depth maps are estimated in the cloud and transmitted along the multiview video. Moreover, a novel depth image-based rendering technique is developed to improve quality while minimizing processing load on the mobile terminal, giving typical peak signal-to-noise ratio gains of 2 dB. Experimental results reveal that, for a satisfactory rendering quality, bit-rate savings of more than 70% are achieved compared with simulcast transmission. Furthermore, subjective tests indicate that this solution improves the perceived quality considerably. Finally, we study the impact of handovers induced in mobile systems on the quality of experience.Index Terms-Depth image-based rendering (DIBR), free-viewpoint television (FTV), long-term evolution (LTE), multiview video coding (MVC), multiview video plus depth (MVD), quality of experience (QoE), 3-D video.

show abstract

Section: A Objective Evaluation Of the Dibr Algorithmsupporting

confidence: 54%

Section: Design Of the Dibr Algorithmmentioning

confidence: 98%

Section: Dibrmentioning

confidence: 99%

See 1 more Smart Citation

Broadcasting Free-Viewpoint Television Over Long-Term Evolution Networks

Zarb

Debono

2016

IEEE Systems Journal

View full text Add to dashboard Cite

show abstract

“…Other DIBR techniques found in literature include the enhancement of virtual views through pixel classification, graph cuts and depthbased inpainting (Tran and Harada 2013) . The perceived depth quality and visual comfort in stereoscopic images are improved using stereoacuity before rendering the images in (Xu et al 2014).…”

Section: Multiview Video Plus Depthmentioning

confidence: 99%

Emerging Imaging Technologies: Trends and Challenges

Domański

Grajek

Conti

et al. 2018

3D Visual Content Creation, Coding and Delivery

View full text Add to dashboard Cite

This chapter addresses image and video technologies related to 3D immersive multimedia delivery systems with special emphasis on the most promising digital formats. Besides recent research results and technical challenges associated with multiview image and image, video and lightfield acquisition and processing, the chapter also presents relevant results from international standardization activities in the scope of ISO, IEC and ITU. Standard solutions to encode multiview image and video content and ongoing research is addressed, along with novel solutions to enable further developments in the emerging technologies dealing with capture and coding for lightfield content and Free Viewpoint Television.

show abstract