EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing
2026-08-18 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the challenge of editing very high-resolution images, which is hard because current models struggle with memory and speed. Instead of generating new images from scratch, their method, EditBridge, improves a low-res edited image into a high-res version by using information from the original high-res source to keep details accurate. They use a smart attention technique that focuses only on matching areas between the images, making the process faster and less memory-heavy. Experiments show their approach works well up to 4K resolution and is much faster than previous methods.
diffusion modelshigh-resolution image editingsuper-resolutionattention mechanismdata-to-data translationsemantic correspondenceblock-wise sparse attentioncomputational efficiency
Authors
Jiayi Song, Shijie Huang, Fangtai Wu, Yubo Huang, Zhenxiong Tan, Songhua Liu, Jiaming Liu, Ruihua Huang
Abstract
High-resolution image editing is increasingly demanded in professional workflows, yet existing diffusion-based models remain constrained to resolutions below 1K due to quadratic attention complexity and prohibitive memory requirements. A prevalent workaround employs a two-stage pipeline: editing at low resolution followed by independent super-resolution. However, this approach suffers from two critical issues: information divergence, where hallucinated details contradict the original high-resolution (HR) source, and texture degradation, manifesting as over-smoothed or over-sharpened artifacts. We propose EditBridge, a diffusion bridge framework for efficient ultra high-resolution editing. Unlike conventional diffusion that regenerates from noise, we formulate refinement as structured data-to-data translation from the low-resolution (LR) edited result to its HR counterpart, explicitly conditioned on the original HR source to preserve authentic details. To efficiently incorporate HR source guidance, we introduce a prior-guided block-wise sparse attention mechanism that exploits semantic correspondence from first-stage editing to constrain cross-image interactions to spatially aligned regions, significantly reducing computational overhead. Extensive experiments demonstrate that EditBridge achieves high-fidelity editing with superior perceptual quality at resolutions up to 4K, delivering 3.6--8.4$\times$ speedup at 2K and enabling practical 4K editing in 61 seconds.