Causal interventional training for image recognition

W Qin, H Zhang, R Hong, EP Lim… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Deep learning models often fit undesired dataset bias in training. In this paper, we formulate
the bias using causal inference, which helps us uncover the ever-elusive causalities among …

Real-time depth video-based rendering for 6-DoF HMD navigation and light field displays

D Bonatto, S Fachada, S Rogge, A Munteanu… - IEEE …, 2021 - ieeexplore.ieee.org
This paper presents a novel approach to provide immersive free navigation with 6 Degrees
of Freedom in real-time for natural and virtual scenery, for both static and dynamic content …

Steered mixture-of-experts for light field images and video: Representation and coding

R Verhack, T Sikora, G Van Wallendael… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Research in light field (LF) processing has heavily increased over the last decade. This is
largely driven by the desire to achieve the same level of immersion and navigational …

PatientHandNet: 3D Open-palm Hand Reconstruction from Sparse Multi-view Depth Images

X Dai, R Zhao, P Hu, A Munteanu - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Accurately reconstructing 3-D hand shapes of patients is important for immobilization device
customization, artificial limb generation, and hand disease diagnosis. Traditional 3-D hand …

Color correction for immersive video applications

A Dziembowski, D Mieloch, S Różek… - IEEE Access, 2021 - ieeexplore.ieee.org
In this paper, the color correction method developed for immersive video systems is
presented. The proposed method significantly increases the consistency of color …

Virtual view synthesis for 3DoF+ video

A Dziembowski, D Mieloch… - 2019 Picture Coding …, 2019 - ieeexplore.ieee.org
The paper reports a new view synthesis method for omnidirectional video with the ability to
slightly displace a virtual viewpoint, ie the paper describes a novel synthesis method for …

TWGAN: Twin discriminator generative adversarial networks

Z Zhang, M Li, H Xie, J Yu, T Liu… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Generative Adversarial Networks (GAN) has become more and more popular these years.
However, it is difficult to train and suffers from the training instability problem. To tackle this …

Spatiotemporal redundancy removal in immersive video coding

A Dziembowski, D Mieloch, M Domański… - 2022 - otik.uk.zcu.cz
In this paper, the authors describe two methods designed for reducing the spatiotemporal
redundancy of the video within the MPEG Immersive video (MIV) encoder: patch occupation …

[PDF][PDF] 6DoF 视频技术研究进展

王旭, 刘琼, 彭宗举, 侯军辉, 元辉, 赵铁松, 秦熠… - 中国图象图形学报, 2023 - cjig.cn
随着元宇宙概念的兴起, 以6 自由度(six degree of freedom, 6DoF) 视频为代表的新一代交互式
媒体技术得到产业界和学术界的广泛关注. 6DoF 视频隶属于多媒体通信领域 …

Bypassing depth maps transmission for immersive video coding

P Garus, J Jung, T Maugey… - 2019 Picture Coding …, 2019 - ieeexplore.ieee.org
This paper addresses several downsides of the system under development in MPEG-I for
coding and transmission of immersive media. We present a solution, which enables Depth …