FlashReFocus: Interactive Image Refocusing in Seconds
In brief
- FlashReFocus runs a diffusion model once per image, then uses a lightweight network for edits.
- The method separates ill-posed image restoration from deterministic blur rendering.
- Results are 148x faster than competing generative approaches for refocusing.
FlashReFocus introduces a new approach to post-capture refocusing by changing depth of field and focal plane. Unlike current generative methods, it runs a diffusion model once per image, then applies edits with a lightweight network in real time.
This summary gives you the essentials. The full article, its figures and quotes are on cs.AI updates on arXiv.org.
Read the original articleAI-generated summary of the source, checked by rules. Report an error