Papers
arxiv:2503.07047

Recovering Partially Corrupted Major Objects through Tri-modality Based Image Completion

Published on Mar 10
Authors:
,
,

Abstract

The VSSA model enhances diffusion models by integrating casual sketches and text prompts to improve fine-grained structural detail recovery in partially obscured images.

AI-generated summary

Diffusion models have become widely adopted in image completion tasks, with text prompts commonly employed to ensure semantic coherence by providing high-level guidance. However, a persistent challenge arises when an object is partially obscured in the damaged region, yet its remaining parts are still visible in the background. While text prompts offer semantic direction, they often fail to precisely recover fine-grained structural details, such as the object's overall posture, ensuring alignment with the visible object information in the background. This limitation stems from the inability of text prompts to provide pixel-level specificity. To address this, we propose supplementing text-based guidance with a novel visual aid: a casual sketch, which can be roughly drawn by anyone based on visible object parts. This sketch supplies critical structural cues, enabling the generative model to produce an object structure that seamlessly integrates with the existing background. We introduce the Visual Sketch Self-Aware (VSSA) model, which integrates the casual sketch into each iterative step of the diffusion process, offering distinct advantages for partially corrupted scenarios. By blending sketch-derived features with those of the corrupted image, and leveraging text prompt guidance, the VSSA assists the diffusion model in generating images that preserve both the intended object semantics and structural consistency across the restored objects and original regions. To support this research, we created two datasets, CUB-sketch and MSCOCO-sketch, each combining images, sketches, and text. Extensive qualitative and quantitative experiments demonstrate that our approach outperforms several state-of-the-art methods.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2503.07047 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2503.07047 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2503.07047 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.