Deep Multi-Domain Prediction for 3D Video Coding

Lei, Jianjun; Shi, Yanan; Pan, Zhaoqing; Liu, Dong; Jin, Dengchao; Chen, Ying; Ling, Nam

doi:10.1109/tbc.2021.3090261

Cited by 15 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For a fair comparison, the fully factorized model [10], hyperprior model [11], and joint autoregressive model [12] are retrained on NYU-Depth V2 dataset. BD-rate and BD-PSNR [19,20] are adopted as the objective evaluation metrics to evaluate the compression performance. The fully factorized model is set as the anchor, and the quantitative comparison results are reported in Table 1.…”

Section: Comparison Resultsmentioning

confidence: 99%

Texture-Guided End-to-End Depth Map Compression

Peng

Jing

Jin

et al. 2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

End-to-end compression methods designed for the texture image have achieved excellent coding performances. Due to the characteristic differences between the depth map and the texture image, the texture-oriented methods have limitations in depth map compression. To address this problem, this paper proposes a texture-guided end-to-end depth map compression network (TDMC-Net). Specifically, the proposed TDMC-Net is mainly composed of the texture-guided transform module (TTM) which performs the nonlinear transform with providing the textual context to reduce the redundancy in depth feature, and a texture-guided conditional entropy model (TCEM) which is designed to improve the entropy model by introducing the texture conditional prior. Experimental results show that the proposed TDMC-Net boosts the depth coding efficiency by utilizing the texture information and achieves superior performance.

show abstract

Section: Comparison Resultsmentioning

confidence: 99%

Texture-Guided End-to-End Depth Map Compression

Peng

Jing

Jin

et al. 2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…Lei et al [17] put forward a deep reference frame generation method for MVC, which converts the parallax between different viewpoints through parallax-guided generation network. Lei et al [16] exploited spatial, temporal, and inter-view correlations and proposed a deep multi-domain prediction for 3D video coding. By employing CNNs to fuse multi-domain references, they achieved significant bitrate savings compared to 3D-HEVC.…”

Section: Deep Learning-based Mvcmentioning

confidence: 99%

Multi-View Video Coding with GAN Latent Learning

Lan¹,

Luo²,

Yan³

et al. 2022

Preprint

View full text Add to dashboard Cite

The introduction of multiple viewpoints inevitably increases the bitrates to store and transmit video scenes. To reduce the compressed bitrates, researchers have developed to skip intermediate viewpoints during compression and delivery, and finally reconstruct them with Side Information (SI). Generally, the depth maps can be utilized to construct SI; however, it shows inferior performance with inaccurate reconstruction or high bitrates. In this paper, we propose a multi-view video coding based on SI of Generative Adversarial Network (GAN). At the encoder, we construct a spatio-temporal Epipolar Plane Image (EPI) and further utilize convolutional network to extract the latent code of GAN as SI; while at the decoder side, we combine the SI and adjacent viewpoints to reconstruct intermediate views by the generator of GAN. In particular, we set a joint encoder constraint of reconstruction cost and SI entropy, in order to achieve an optimal tradeoff between reconstruction quality and bitrate overhead. Experiments show a significantly improved Rate-Distortion (RD) performance compared with the state-of-the-art methods.

show abstract

“…Since then, other articles published target topics of very much traction lately. For example, researchers interested in innovative 5G solutions involving machine learning are advised to read articles [28]- [31] and those interested in solutions targeting the latest media formats papers [16], [33], [34]. Other papers in broadcasting-related areas of focus include [A1], [35], [36].…”

Section: Media Production and The Transition Toward Ip And Cloudmentioning

confidence: 99%