TurboClear: One-Step Object-Effect Removal via Region-Calibrated Distribution Matching and Fusion
This work addresses the high inference cost of multi-step diffusion models for object-effect removal, offering a more efficient solution for applications requiring real-time or faster processing.
This paper introduces TurboClear, a one-step SDXL-based model for removing objects and their associated effects from images. It achieves significant improvements in inference efficiency, reducing computational overhead by up to 40.04x compared to ObjectClear and 665x against OmniPaint, while maintaining comparable or better visual quality.
Recently, diffusion-based removal methods have achieved promising visual quality in removing both target objects and their associated effects. However, they typically rely on multi-step denoising, leading to high inference cost. Directly applying existing one-step distillation methods is also suboptimal, since their global objectives lack explicit region-wise calibration and may weaken the asymmetric edit-and-preserve behavior required by object-effect removal. To address these challenges, we propose TurboClear, a one-step SDXL-based object-effect removal model. During training, we design Region-Calibrated Distribution Matching (RDM) for region-aware distillation to preserve the teacher model's asymmetric edit-and-preserve behavior. Furthermore, we propose Learnable Spatial Fusion (LSF) for lightweight inference-time fusion. Extensive experiments show that TurboClear significantly improves inference efficiency while maintaining competitive visual quality. TurboClear reduces the computational overhead by up to $40.04\times$ compared to ObjectClear, and by up to $665\times$ against the Flux-based method OmniPaint, all while maintaining comparable or better visual removal quality. Code is available at https://github.com/GuoCalix/TurboClear.