Memory Efficient VDB-Based Radiance Fields for Fast Training and Rendering

CVPR 2023

In this paper, we present a new representation for neural radiance fields that accelerates both the training and the inference processes with VDB, a hierarchical data structure for sparse volumes. VDB takes both the advantages of sparse and dense volumes for compact data representation and efficient data access, being a promising data structure for NeRF data interpolation and ray marching. Our method, Plenoptic VDB (PlenVDB), directly learns the VDB data structure from a set of posed images by means of a novel training strategy and then uses it for real-time rendering. Experimental results demonstrate the effectiveness and the efficiency of our method over previous arts: First, it converges faster in the training process. Second, it delivers a more compact data format for NeRF data presentation. Finally, it renders more efficiently on commodity graphics hardware. Our mobile PlenVDB demo achieves 30+ FPS, 1280x720 resolution on an iPhone12 mobile phone.


Given a set of training views, our method directly optimizes a VDB model. Then a novel view can be rendered with the model. The potential of VDB is due to two advantages: fast voxel access for faster speed, and efficient storage for smaller model size. This enables efficient NeRF rendering on mobile devices.


This website is in part based on a template of Michaël Gharbi, also used in PixelNeRF and PlenOctrees.