Efficient Neural Radiance Fields for Interactive Free-viewpoint Video

SIGGRAPH Asia 2022 (Conference Track)

Haotong Lin*, Sida Peng*, Zhen Xu, Yunzhi Yan, Qing Shuai, Hujun Bao, Xiaowei Zhou

State Key Lab of CAD & CG, Zhejiang University
* denotes equal contribution


This paper aims to tackle the challenge of efficiently producing interactive free-viewpoint videos. Some recent works equip neural radiance fields with image encoders, enabling them to generalize across scenes. When processing dynamic scenes, they can simply treat each video frame as an individual scene and perform novel view synthesis to generate free-viewpoint videos. However, their rendering process is slow and cannot support interactive applications. A major factor is that they sample lots of points in empty space when inferring radiance fields. We propose a novel scene representation, called ENeRF, for the fast creation of interactive free-viewpoint videos. Specifically, given multi-view images at one frame, we first build the cascade cost volume to predict the coarse geometry of the scene. The coarse geometry allows us to sample few points near the scene surface, thereby significantly improving the rendering speed. This process is fully differentiable, enabling us to jointly learn the depth prediction and radiance field networks from RGB images. Experiments on multiple benchmarks show that our approach exhibits competitive performance while being at least 60 times faster than previous generalizable radiance field methods.

Overview video

Interactive free-viewpoint video demo on the ZJU-MoCap and ST-NeRF datasets

More results on dynamic scenes


  title={Efficient Neural Radiance Fields for Interactive Free-viewpoint Video},
  author={Lin, Haotong and Peng, Sida and Xu, Zhen and Yan, Yunzhi and Shuai, Qing and Bao, Hujun and Zhou, Xiaowei},
  booktitle={SIGGRAPH Asia Conference Proceedings},