Towards Full-scene Volumetric Video Streaming via Spatially Layered Representation and NeRF Generation
Jianxin Shi, Miao Zhang, Linfeng Shen, Jiangchuan Liu, Yuan Zhang, Lingjun Pu, Jingdong Xu · 2024
Immersive full-scene volumetric video (VV) showcases the richness and detail of the 3D world, yet poses significant streaming challenges given its massive data volume. Existing 3D tile-based viewport approaches struggle to effectively adapt to full-scene VV owing to their small video buffer limitation, high tile segmentation overhead, and lack of full-scene consideration.