Session: | Point Clouds, 360 and Volumetric Data |
Location: | Lecture Room |
Session Time: | Tuesday, June 26, 13:40 - 15:20 |
Presentation Time: | Tuesday, June 26, 13:40 - 14:00 |
Presentation: |
Lecture
|
Paper Title: |
IMAGE-BASED RENDERING USING POINT CLOUD FOR 2D VIDEO COMPRESSION |
Authors: |
Hossein Bakhshi Golestani; RWTH Aachen University, Germany | | |
| Thibaut Meyer; RWTH Aachen University, Germany | | |
| Mathias Wien; RWTH Aachen University, Germany | | |
Abstract: |
The main idea of this paper is to extract the 3D scene geometry for the observed scene and use it for synthesizing a more precise prediction using Image-Based Rendering (IBR) for motion compensation in a hybrid coding scheme. The proposed method first extracts camera parameters using Structure from Motion (SfM). Then, a Patch-based Multi-View Stereo (PMVS) technique is employed to generate the scene Point-Cloud (PC) only from already decoded key-frames. Since the PC could be really sparse in poorly reconstructed regions, a depth expansion mechanism is also used. This 3D information helps to properly warp textures from the key-frames to the target frame. This IBR-based prediction is then used as an additional reference for motion compensation. In this way, the encoder can choose between the rendered prediction and the regular reference pictures through a rate-distortion optimization. On average, the simulation results show about 2.16% bitrate reduction compared to the reference HEVC implementation, for tested dynamic and static scene video sequences. |