Precise Object and Effect Removal with Adaptive Target-Aware Attention

TL;DR

ObjectClear introduces an adaptive attention-based framework for precise removal of objects and their effects, significantly improving background fidelity and visual consistency in complex scenes.

Contribution

The paper presents ObjectClear, a novel method with adaptive target-aware attention for accurate object and effect removal, and introduces the OBER dataset for training and evaluation.

Findings

Outperforms prior methods in object-effect removal quality

Achieves higher background fidelity in complex scenes

Demonstrates robustness across diverse objects and effects

Abstract

Object removal requires eliminating not only the target object but also its associated visual effects such as shadows and reflections. However, diffusion-based inpainting and removal methods often introduce artifacts, hallucinate contents, alter background, and struggle to remove object effects accurately. To address these challenges, we propose ObjectClear, a novel framework that decouples foreground removal from background reconstruction via an adaptive target-aware attention mechanism. This design empowers the model to precisely localize and remove both objects and their effects while maintaining high background fidelity. Moreover, the learned attention maps are leveraged for an attention-guided fusion strategy during inference, further enhancing visual consistency. To facilitate the training and evaluation, we construct OBER, a large-scale dataset for OBject-Effect Removal, which provides paired images with and without object-effects, along with precise masks for both objects and their effects. The dataset comprises high-quality captured and simulated data, covering diverse objects, effects, and complex multi-object scenes. Extensive experiments demonstrate that ObjectClear outperforms prior methods, achieving superior object-effect removal quality and background fidelity, especially in challenging scenarios.