INVE: Interactive Neural Video Editing

TL;DR

INVE is a real-time neural video editing system that efficiently propagates sparse frame edits across videos, supporting diverse editing operations with significantly faster processing than previous methods.

Contribution

The paper introduces INVE, a novel neural video editing approach that leverages hash-grid encoding and vectorized editing to enable fast, versatile, and interactive video editing.

Findings

INVE reduces learning and inference time by a factor of 5 compared to LNA.

Supports a wider range of editing operations than LNA.

Demonstrates superior performance through quantitative and qualitative analysis.

Abstract

We present Interactive Neural Video Editing (INVE), a real-time video editing solution, which can assist the video editing process by consistently propagating sparse frame edits to the entire video clip. Our method is inspired by the recent work on Layered Neural Atlas (LNA). LNA, however, suffers from two major drawbacks: (1) the method is too slow for interactive editing, and (2) it offers insufficient support for some editing use cases, including direct frame editing and rigid texture tracking. To address these challenges we leverage and adopt highly efficient network architectures, powered by hash-grids encoding, to substantially improve processing speed. In addition, we learn bi-directional functions between image-atlas and introduce vectorized editing, which collectively enables a much greater variety of edits in both the atlas and the frames directly. Compared to LNA, our INVE reduces the learning and inference time by a factor of 5, and supports various video editing operations that LNA cannot. We showcase the superiority of INVE over LNA in interactive video editing through a comprehensive quantitative and qualitative analysis, highlighting its numerous advantages and improved performance. For video results, please see https://gabriel-huang.github.io/inve/