Results 1 to 10 of about 5,219,664 (202)

On the Selection of Transmitted Views for Decoder-Side Depth Estimation

Applied Sciences
The selection of optimal views for transmission is critical for the coding efficiency of the MPEG Immersive Video (MIV) profile of Decoder-Side Depth Estimation (DSDE).
Dominika Klóska, Adrian Dziembowski, Adam Grzelka, Dawid Mieloch   +3 more
doaj   +5 more sources

On Alpha-Expansion-Based Graph-Cut Optimization for Decoder-Side Depth Estimation

Applied Sciences
In order to achieve high realism an acceptable level of user experience in immersive videos, it is crucial to provide both the best possible quality of depth maps and minimize computational time.
Dawid Mieloch, Dominika Klóska, Olgierd Stankiewicz   +2 more
doaj   +5 more sources

Motion Compensation-based Low-Complexity Decoder Side Depth Estimation for MPEG Immersive Video [PDF]

2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP), 2022
Decoder-Side Depth Estimation (DSDE) is a system firstly enabled in the novel MPEG Immersive Video (MIV) coding standard. In DSDE, only texture components are coded, while the depth is estimated at the decoder-side. This is motivated by previous work, which has shown high coding gain and pixel rate savings in DSDE. However, the computational complexity
Thomas Maugey, Christine Guillemot, Patrick Garus   +2 more
exaly   +4 more sources

Recursive block splitting in feature-driven decoder-side depth estimation [PDF]

ETRI Journal, 2022
This paper presents a study on the use of encoder-derived features in decoder-side depth estimation. The scheme of multiview video encoding does not require the transmission of depth maps (which carry the geometry of a three-dimensional scene) as only a ...
Błażej Szydełko, Adrian Dziembowski, Dawid Mieloch, Marek Domański, Gwangsoon Lee   +4 more
doaj   +2 more sources

Overview and Efficiency of Decoder-Side Depth Estimation in MPEG Immersive Video

IEEE Transactions on Circuits and Systems for Video Technology, 2022
Joel Jung, Dawid Mieloch, Basel Salahieh   +2 more
exaly   +3 more sources

Constructing 3D Object Detectors Based on Deformable Convolutional Guided Depths

IEEE Access
This paper introduces a depth-guided 3D object detection method that enhances the feature extraction capability of the backbone network through weak supervision. It combines large kernel convolution, global response normalization, and layer normalization
Xinwang Zheng, Guangsong Yang, Lu Yang, Chengyu Lu   +3 more
doaj   +1 more source

Light Attention Encoder-Decoder for Cattle Body Segmentation and Body Weight Estimation. [PDF]

Animals (Basel)
Mann SS, Shehada HK, Amorim ST, Ha DS, Morota G, Shin S.   +5 more
europepmc   +1 more source

Geometric Feature Relationship-Based Knowledge Distillation for Ground Reaction Force Estimation. [PDF]

Measurement (Lond)
Lim H, Lee J, Save OM, Lee H, Turaga P, Jeon ES.   +5 more
europepmc   +1 more source

Improving dual-panel in-beam PET imaging for proton therapy monitoring using 3D U-Net. [PDF]

Med Phys
Mu D, Qi P, Qiu A, Liu Q, Ma Q, Xiao P, Wan L, Li B, Deng J, Qiu B, Yang Z, Xie Q.   +11 more
europepmc   +1 more source

WeatherMono: A CNN-Transformer Architecture for Self-Supervised Monocular Depth Estimation in Rainy and Foggy Conditions. [PDF]

Sensors (Basel)
Qiu Y.
europepmc   +1 more source