Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes

Code

• github.com/zhengqili/Neural-Scene-Flow-Fields
  pytorch★ 741
• github.com/zl548/neural-scene-flow-fields
  pytorch★ 741
• github.com/kwea123/nsff_pl
  pytorch★ 224

Abstract

We present a method to perform novel view and time synthesis of dynamic scenes, requiring only a monocular video with known camera poses as input. To do this, we introduce Neural Scene Flow Fields, a new representation that models the dynamic scene as a time-variant continuous function of appearance, geometry, and 3D scene motion. Our representation is optimized through a neural network to fit the observed input views. We show that our representation can be used for complex dynamic scenes, including thin structures, view-dependent effects, and natural degrees of motion. We conduct a number of experiments that demonstrate our approach significantly outperforms recent monocular view synthesis methods, and show qualitative results of space-time view synthesis on a variety of real-world videos.

Reproductions