CVMay 9

FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching

arXiv:2605.0900370.5
AI Analysis

For users of image editing tools, this work drastically reduces inference time for object removal without sacrificing quality, addressing a key practical bottleneck.

FlashClear accelerates diffusion-based object removal by up to 122x over OmniPaint and 8.26x over ObjectClear on the OBER benchmark, while maintaining high visual quality, using region-aware distillation and feature caching.

Recently, diffusion-based object removal models have achieved impressive results in eliminating objects and their associated visual effects. However, they indiscriminately denoise all tokens across all timesteps, ignoring that removal usually involves small foreground regions. This strategy introduces substantial computational overhead and prolonged inference times. To overcome this computational burden, we propose a latent discriminator to implement Region-aware Adversarial Distillation (RAD), yielding a highly efficient few-step model named FlashClear. Furthermore, tailored to few-step diffusion models, we propose FPAC (Foreground-Prioritized Asymmetric Attention and Caching), a training-free acceleration strategy. Extensive experiments demonstrate that our framework provides massive acceleration while maintaining or exceeding the performance of our base model, ObjectClear. Notably, on the OBER benchmark, our FlashClear achieves up to 8.26$\times$ and 122$\times$ speedup over ObjectClear and OmniPaint, respectively, while maintaining high visual quality and fidelity.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes