Saved in:
Bibliographic Details
Main Authors: Tang, Yixin, Guo, Jiawei, Li, Junxian, Li, Zhiteng, Zhao, Jixin, Zhang, Bingya, Wang, Chenbo, Zhang, Yulun, Zhou, Shangchen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.09003
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917483061968896
author Tang, Yixin
Guo, Jiawei
Li, Junxian
Li, Zhiteng
Zhao, Jixin
Zhang, Bingya
Wang, Chenbo
Zhang, Yulun
Zhou, Shangchen
author_facet Tang, Yixin
Guo, Jiawei
Li, Junxian
Li, Zhiteng
Zhao, Jixin
Zhang, Bingya
Wang, Chenbo
Zhang, Yulun
Zhou, Shangchen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_09003
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching
Tang, Yixin
Guo, Jiawei
Li, Junxian
Li, Zhiteng
Zhao, Jixin
Zhang, Bingya
Wang, Chenbo
Zhang, Yulun
Zhou, Shangchen
Computer Vision and Pattern Recognition
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.
title FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.09003