# MatAnyone-E Runs 4K Video Matting at 28.62 Frames per Second on One H200 by Limiting High-Resolution Work to Uncertain Regions

The method claims a 7.4x speedup and 13.1x lower peak memory than MatAnyone 2, while national labs using Meta's open vision models have cut beamline analysis from a month to 15 minutes.

- Published: 2026-10-28T06:21:21.801Z
- Canonical: https://polylog.news/ai/2026-10-28/matanyone-e-runs-4k-video-matting-at-28-62-frames-per-second
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news), [Meta AI](https://ai.meta.com/blog/genesis-mission-lawrence-berkeley-national-laboratory-segment-anything-dino/)

Researchers including Shuyun Wang, Shangchen Zhou and Chen Change Loy posted MatAnyone-E, an efficient extension of the MatAnyone 2 video-matting model, on October 26. The method first propagates memory at low resolution to find uncertain r…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-28/matanyone-e-runs-4k-video-matting-at-28-62-frames-per-second (subscription information: https://polylog.news/pricing).