The authors designed a canvas instruction interface: circles identify objects or regions, scribbles indicate removal, arrows specify movement, and short notes placed near marks describe desired content.
Canvas instructions enable precise image editing without separate text prompts.
VibeEdit uses spatial marks and short notes placed directly on the image to specify edits, outperforming text-only baselines on a benchmark of similar-object scenes.
Big Tech
Jinjing Zhao · Fangyun Wei · Yitong Wang · Xiuyu Wu · Yunuo Chen · Yang Yue · +6 more
University of Sydney · Microsoft Research · Fudan University · Nankai University · Shanghai Jiao Tong University
Research Digest··3 min read
The authors introduce VibeEdit, an image editor that follows canvas instructions—circles, scribbles, arrows, and optional short notes placed directly on an image—to perform object addition, removal, replacement, attribute change, and movement.
Why this paper
From Microsoft Research and 7 others
In one line
Image editing can be directed by drawing marks and notes on the image; VibeEdit outperforms text-prompted baselines on targeted edits among similar objects.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§