Hashing Neural Video Decomposition
with Multiplicative Residuals in Space-Time
ICCV 2023

Abstract

We present a video decomposition method that facilitates layer-based editing of videos with spatiotemporally varying lighting and motion effects. Our neural model decomposes an input video into multiple layered representations, each comprising a 2D texture map, a mask for the original video, and a multiplicative residual characterizing the spatiotemporal variations in lighting conditions. A single edit on the texture maps can be propagated to the corresponding locations in the entire video frames while preserving other contents' consistencies. Our method efficiently learns the layer-based neural representations of a 1080p video in 25s per frame via coordinate hashing and allows real-time rendering of the edited result at 71 fps on a single GPU. Qualitatively, we run our method on various videos to show its effectiveness in generating high-quality editing effects. Quantitatively, we propose to adopt feature-tracking evaluation metrics for objectively assessing the consistency of video editing.

Reconstruction

Reconstruction (1080p)

Video Editing

Camera Motion Control

Compare with Previous Works

Acknowledgements

This work was supported in part by NSTC grants 111-2221-E-001-011-MY2 and 112-2221-E-A49-100-MY3 of Taiwan. We are grateful to National Center for High-performance Computing for providing computational resources and facilities.