Lazy diffusion transformer for interactive image editing

Y Nitzan, Z Wu, R Zhang, E Shechtman… - … on Computer Vision, 2024 - Springer
We introduce a novel diffusion transformer, LazyDiffusion, that generates partial image
updates efficiently. Our approach targets interactive image editing applications in which …

[HTML][HTML] Uncertainty-aware image inpainting with adaptive feedback network

X Ma, X Zhou, H Huang, G Jia, Y Wang, X Chen… - Expert Systems with …, 2024 - Elsevier
While most image inpainting methods perform well on small image defects, they still struggle
to deliver satisfactory results on large holes due to insufficient image guidance. To address …

Transformer-based image and video inpainting: current challenges and future directions

O Elharrouss, R Damseh, AN Belkacem… - Artificial Intelligence …, 2025 - Springer
Image inpainting is currently a hot topic within the field of computer vision. It offers a viable
solution for various applications, including photographic restoration, video editing, and …

Magiceraser: Erasing any objects via semantics-aware control

F Li, Z Zhang, Y Huang, J Liu, R Pei, B Shao… - European Conference on …, 2024 - Springer
The traditional image inpainting task aims to restore corrupted regions by referencing
surrounding background and foreground. However, the object erasure task, which is in …

Weakly supervised semantic segmentation via saliency perception with uncertainty-guided noise suppression

X Liu, G Huang, X Yuan, Z Zheng, G Zhong, X Chen… - The Visual …, 2024 - Springer
Abstract Weakly Supervised Semantic Segmentation (WSSS) has become increasingly
popular for achieving remarkable segmentation with only image-level labels. Current WSSS …

High-fidelity document stain removal via a large-scale real-world dataset and a memory-augmented transformer

M Li, H Sun, Y Lei, X Zhang, Y Dong, Y Zhou… - arxiv preprint arxiv …, 2024 - arxiv.org
Document images are often degraded by various stains, significantly impacting their
readability and hindering downstream applications such as document digitization and …

Test-time intensity consistency adaptation for shadow detection

L Zhu, W Liu, X Chen, Z Li, X Chen, Z Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Shadow detection is crucial for accurate scene understanding in computer vision, yet it is
challenged by the diverse appearances of shadows caused by variations in illumination …

Stereocrafter: Diffusion-based generation of long and high-fidelity stereoscopic 3d from monocular videos

S Zhao, W Hu, X Cun, Y Zhang, X Li, Z Kong… - arxiv preprint arxiv …, 2024 - arxiv.org
This paper presents a novel framework for converting 2D videos to immersive stereoscopic
3D, addressing the growing demand for 3D content in immersive experience. Leveraging …

SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting

J Wu, Y Feng, H Xu, C Zhu, J Zheng - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Image inpainting is in full bloom accompanied by the progress of convolutional neural
networks (CNNs) and transformers, revolutionizing the practical management of abnormity …

Ancient paintings inpainting based on dual encoders and contextual information

Z Sun, Y Lei, X Wu - Heritage Science, 2024 - Springer
Deep learning-based inpainting models have achieved success in restoring natural images,
yet their application to ancient paintings encounters challenges due to the loss of texture …