Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes | Cornell
CrossMind.ai logo

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

Dec 21, 2020
|
56 views
|
Details
Using a video input, Cornell University researchers trained a neural network to be able to alter the viewpoint and time of the video while in motion. 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.

Comments
loading...