Litcius/Paper detail

Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Design

Yonggan Fu, Zhifan Ye, Jiayi Yuan, Shunyao Zhang, Sixu Li, Haoran You, Yingyan Lin

202333 citationsDOIOpen Access PDF

Abstract

Novel view synthesis is an essential functionality for enabling immersive experiences in various Augmented- and Virtual-Reality (AR/VR) applications, for which Neural Radiance Field (NeRF) has emerged as the state-of-the-art (SOTA) technique. In particular, generalizable NeRFs have gained increasing popularity thanks to their cross-scene generalization capability, which enables NeRFs to be instantly serviceable for new scenes without per-scene training. Despite their promise, generalizable NeRFs aggravate the prohibitive complexity of NeRFs due to their required extra memory accesses needed to acquire scene features, causing NeRFs' ray marching process to be memory-bounded. To tackle this dilemma, existing sparsity-exploitation techniques for NeRFs fall short, because they require knowledge of the sparsity distribution of the target 3D scene which is unknown when generalizing NeRFs to a new scene.

Topics & Concepts

Computer scienceGeneralizationPopularityProcess (computing)Field (mathematics)Virtual realityState (computer science)Artificial intelligenceAlgorithmMathematicsPsychologyMathematical analysisSocial psychologyPure mathematicsOperating system3D Shape Modeling and AnalysisAdvanced Vision and ImagingComputer Graphics and Visualization Techniques
Gen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-Design | Litcius