CSF-Net: Context-Semantic Fusion Network for Large Mask Inpainting
In this paper, we propose a semantic-guided framework to address the challenging problem of large-mask image inpainting, where essential visual content is missing and contextual cues are limited. To compensate for the limited context, we leverage a pretrained Amodal Completion (AC) model to generate structure-aware candidates that serve as semantic priors for the missing regions. We introduce Context-Semantic Fusion Network (CSF-Net), a transformer-based fusion framework that fuses these candidates with contextual features to produce a semantic guidance image for image inpainting. This guidance improves inpainting quality by promoting structural accuracy and semantic consistency. CSF-Net can be seamlessly integrated into existing inpainting models without architectural changes and consistently enhances performance across diverse masking conditions. Extensive experiments on the Places365 and COCOA datasets demonstrate that CSF-Net effectively reduces object hallucination while enhancing visual realism and semantic alignment. The code for CSF-Net is available at https://github.com/chaeyeonheo/CSF-Net.
Code (0)
등록된 구현이 없습니다.
Tasks
Image InpaintingSimilar Papers 제목 키워드 기반
3D-Consistent Image Inpainting with Diffusion Models
We address the problem of 3D inconsistency of image inpainting based on diffusion models. We propose a generative model using image pairs that belong to the same scene. To achieve the 3D-consistent and semantically coher…
DenoisingImage InpaintingInductive BiasGuidPaint: Class-Guided Image Inpainting with Diffusion Models
In recent years, diffusion models have been widely adopted for image inpainting tasks due to their powerful generative capabilities, achieving impressive results. Existing multimodal inpainting methods based on diffusion…
Image InpaintingMTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting
Advancements in generative models have enabled image inpainting models to generate content within specific regions of an image based on provided prompts and masks. However, existing inpainting methods often suffer from p…
Image InpaintingImproving Text-guided Object Inpainting with Semantic Pre-inpainting
Recent years have witnessed the success of large text-to-image diffusion models and their remarkable potential to generate high-quality images. The further pursuit of enhancing the editability of images has sparked signi…
DenoisingObjectIS-Diff: Improving Diffusion-Based Inpainting with Better Initial Seed
Diffusion models have shown promising results in free-form inpainting. Recent studies based on refined diffusion samplers or novel architectural designs led to realistic results and high data consistency. However, random…