DeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay Removal
Video overlay removal aims to recover scenes obscured by subtitles, titles, and logos while preserving surrounding content. Existing methods use temporal propagation or source-conditioned generation, but can leave residual overlays and distort scene structure when useful source information is obscured. We propose DeOverlay, a source-anchored flow model that reconstructs the clean video from the source latent with fixed source guidance. Specifically, we train a shared velocity network along paired source-to-clean paths using region-weighted flow matching, enabling successive cor- rections from intermediate states. To select local source cues, we develop visibility-normalized temporal aggre...
| Authors | Deshui Miao, Yuhang Ma, Shaoyong Jia et al. |
|---|---|
| Primary category | cs.CV |
| Published | 19 October 2026 |
| Last updated at source | 19 October 2026 |
Recent changes
- 20 Oct 2026 Description: Video overlay removal aims to recover scenes obscured by subtitles, titles, and logos while preserving surrounding content. Existing methods use temporal propagation or source-conditioned generation, but can leave residual overlays and dist → Video overlay removal aims to recover scenes obscured by subtitles, titles, and logos while preserving surrounding content. Existing methods use temporal propagation or source-conditioned generation, but can leave residual overlays and dist
- 20 Oct 2026 Topics added cs.CV removed hf-daily-papers, flow matching, velocity network, region-weighted flow matching, visibility-normalized temporal aggregation, additive conditioning, video-token sequence, dvte-bench, mask lpips
Changes detected by Silytics between refreshes of the source.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 20 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.