FlashReFocus：单图交互式重新对焦，后续编辑仅需约半秒
FlashReFocus: Interactive Image Refocusing in Seconds
一篇很实用的图像编辑论文：跑一次扩散模型，之后改焦点只要半秒，比 GenRefocus 快 462 倍，还附带了自建的 3 相机测试集。
FlashReFocus 是一种单张照片重新对焦方法，把恢复全清晰图像和渲染模糊拆成两个子问题：前者用一步扩散去模糊器加解码器精修恢复细节，后者用条件于显式散焦图和散焦偏置注意力的轻量网络渲染模糊。
每张照片只需运行一次扩散模型，之后每次编辑约 0.5 秒完成，比 GenRefocus 的进一步编辑快 462 倍，整体重新对焦快 148.
3 倍。作者还收集了包含 3 台相机、89 组图像对的 3CReal 基准，用于测试对未见相机的泛化能力。
该方法在 EBB!和 3CReal 两个基准上取得零样本散景渲染的最佳感知保真度，且支持移轴和双焦平面编辑。
FlashReFocus: Interactive Image Refocusing in Seconds
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.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include FlashReFocus, 扩散模型, 图像编辑, 散景渲染.
Source attribution: curated from arXiv cs.AI (@Ching-Heng Cheng, Chia-Ming Lee, Ming-Ching Chang, Xin Li, Yu-Lun Liu, Chih-Chung Hsu).