Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.06065 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914182945832960 |
|---|---|
| author | Li, Runjia Haji-Ali, Moayed Mirzaei, Ashkan Wang, Chaoyang Sahni, Arpit Skorokhodov, Ivan Siarohin, Aliaksandr Jakab, Tomas Han, Junlin Tulyakov, Sergey Torr, Philip Menapace, Willi |
| author_facet | Li, Runjia Haji-Ali, Moayed Mirzaei, Ashkan Wang, Chaoyang Sahni, Arpit Skorokhodov, Ivan Siarohin, Aliaksandr Jakab, Tomas Han, Junlin Tulyakov, Sergey Torr, Philip Menapace, Willi |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_06065 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing Li, Runjia Haji-Ali, Moayed Mirzaei, Ashkan Wang, Chaoyang Sahni, Arpit Skorokhodov, Ivan Siarohin, Aliaksandr Jakab, Tomas Han, Junlin Tulyakov, Sergey Torr, Philip Menapace, Willi Computer Vision and Pattern Recognition Artificial Intelligence 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 |
| title | EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.06065 |