Lazy diffusion transformer for interactive image editing
We introduce a novel diffusion transformer, LazyDiffusion, that generates partial image
updates efficiently. Our approach targets interactive image editing applications in which …
updates efficiently. Our approach targets interactive image editing applications in which …
[HTML][HTML] Uncertainty-aware image inpainting with adaptive feedback network
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 …
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
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 …
solution for various applications, including photographic restoration, video editing, and …
Magiceraser: Erasing any objects via semantics-aware control
The traditional image inpainting task aims to restore corrupted regions by referencing
surrounding background and foreground. However, the object erasure task, which is in …
surrounding background and foreground. However, the object erasure task, which is in …
Weakly supervised semantic segmentation via saliency perception with uncertainty-guided noise suppression
Abstract Weakly Supervised Semantic Segmentation (WSSS) has become increasingly
popular for achieving remarkable segmentation with only image-level labels. Current WSSS …
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
Document images are often degraded by various stains, significantly impacting their
readability and hindering downstream applications such as document digitization and …
readability and hindering downstream applications such as document digitization and …
Test-time intensity consistency adaptation for shadow detection
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 …
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
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 …
3D, addressing the growing demand for 3D content in immersive experience. Leveraging …
SyFormer: Structure-Guided Synergism Transformer for Large-Portion Image Inpainting
Image inpainting is in full bloom accompanied by the progress of convolutional neural
networks (CNNs) and transformers, revolutionizing the practical management of abnormity …
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 …
yet their application to ancient paintings encounters challenges due to the loss of texture …