Flashrefocus enables fast interactive image refocusing after capture
FlashReFocus: Interactive Image Refocusing in Seconds
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Changing the focus and blur of a photo after it's taken usually requires a slow, complex process. The authors show that by separating the problem into two parts—finding the sharp original image and then adding blur—they can work much faster. They use a single detailed processing step followed by a lightweight step for quick edits, letting users try new focus settings instantly. They also created a new dataset to test their method on photos from different cameras and found that their approach is much faster and yields better-looking results than previous ones.
What this means in practice
- •For photo editing software developers: Add fast interactive focus and blur editing to photos using a single initial model run and quick subsequent edits.
- •For smartphone camera app developers: Implement real-time post-capture refocusing features with high visual quality and low latency on device.$Commercial implications: Enables development of camera apps that sell advanced interactive refocusing capabilities to smartphone users.
Authors
Ching-Heng Cheng, Chia-Ming Lee, Ming-Ching Chang, Xin Li, Yu-Lun Liu, Chih-Chung Hsu
Abstract
Single-image refocusing changes the focal plane and depth of field of a photograph after capture. It is inherently interactive: users try many focal points and blur strengths on one image, so each edit should be fast and change only the blur. Recent generative methods, however, rerun large diffusion models for every edit. We observe that the two sub-problems differ in kind: recovering the all-in-focus image is ill-posed and needs a generative prior, whereas rendering blur is largely determined by depth and the focal plane. We therefore propose FlashReFocus, which runs diffusion once per photograph and renders every edit with a lightweight network. To address the ill-posed restoration, a one-step diffusion deblurrer with a decoder refiner recovers fine detail efficiently while balancing fidelity and perceptual quality. For precise control, the renderer is conditioned on an explicit defocus map and uses defocus-bias attention, which lets pixels at similar defocus share information without interference from pixels at other depths; in-focus content stays unchanged, and editing the map yields tilt-shift and two focal planes. To further test generalization to unseen cameras, we collect 3CReal, a three-camera benchmark of 89 pairs. FlashReFocus achieves the best perceptual fidelity for zero-shot bokeh rendering on EBB! and 3CReal, refocuses 148.3x faster than GenRefocus, and takes about half a second per further edit, 462x faster.