EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing

TL;DR

EgoEdit introduces a new dataset, real-time editing model, and benchmark for egocentric videos, addressing domain-specific challenges like rapid motion and hand interactions to enable interactive AR applications.

Contribution

The paper presents EgoEdit, a novel real-time egocentric video editor, along with a curated dataset and benchmark, advancing interactive AR video editing capabilities.

Findings

EgoEdit achieves temporally stable, instruction-faithful editing results.

It outperforms existing methods on egocentric editing benchmarks.

Maintains performance comparable to top baselines on general editing tasks.

Abstract

We study instruction-guided editing of egocentric videos for interactive AR applications. While recent AI video editors perform well on third-person footage, egocentric views present unique challenges - including rapid egomotion and frequent hand-object interactions - that create a significant domain gap. Moreover, existing offline editing pipelines suffer from high latency, limiting real-time interaction. To address these issues, we present a complete ecosystem for egocentric video editing. First, we construct EgoEditData, a carefully designed and manually curated dataset specifically designed for egocentric editing scenarios, featuring rich hand-object interactions, while explicitly preserving hands. Second, we develop EgoEdit, an instruction-following egocentric video editor that supports real-time streaming inference on a single GPU. Finally, we introduce EgoEditBench, an evaluation suite targeting instruction faithfulness, hand and interaction preservation, and temporal stability under egomotion. Across both egocentric and general editing tasks, EgoEdit produces temporally stable, instruction-faithful results with interactive latency. It achieves clear gains on egocentric editing benchmarks-where existing methods struggle-while maintaining performance comparable to the strongest baselines on general editing tasks. EgoEditData and EgoEditBench will be made public for the research community. See our website at https://snap-research.github.io/EgoEdit