Litcius/Paper detail

Cambricon-R: A Fully Fused Accelerator for Real-Time Learning of Neural Scene Representation

Xinkai Song, Yuanbo Wen, Xing Hu, Tianbo Liu, H. Zhou, Husheng Han, Tian Zhi, Zidong Du, Wei Li, Rui Zhang, Chen Zhang, Lin Gao, Qi Guo, Tianshi Chen

202312 citationsDOIOpen Access PDF

Abstract

Neural scene representation (NSR) initiates a new methodology of encoding a 3D scene with neural networks by learning from dozens of photos taken from different camera positions. NSR not only achieves significant improvement in the quality of novel view synthesis and 3D reconstruction but also reduces the camera cost from the expensive laser cameras to the cheap color cameras on the shelf. However, performing 3D scene encoding using NSR is far from real-time due to the extremely low hardware utilization (only utilization of hardware peak performance), which greatly limits its applications in real-time AR/VR interactions

Topics & Concepts

Encoding (memory)Computer scienceArtificial intelligenceRepresentation (politics)Artificial neural networkComputer visionComputer graphics (images)PoliticsPolitical scienceLawComputer Graphics and Visualization Techniques3D Shape Modeling and AnalysisAdvanced Vision and Imaging