Sketchedit: Mask-free local image manipulation with partial sketches

Y Zeng, Z Lin, VM Patel - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
Sketch-based image manipulation is an interactive image editing task to modify an image
based on input sketches from users. Existing methods typically convert this task into a …

Contrastive learning for diverse disentangled foreground generation

Y Li, Y Li, J Lu, E Shechtman, YJ Lee… - European Conference on …, 2022 - Springer
We introduce a new method for diverse foreground generation with explicit control over
various factors. Existing image inpainting based foreground generation methods often …

Scene graph driven text-prompt generation for image inpainting

T Shukla, P Maheshwari, R Singh… - Proceedings of the …, 2023 - openaccess.thecvf.com
Scene editing methods are undergoing a revolution, driven by text-to-image synthesis
methods. Applications in media content generation have benefited from a careful set of …

Image inpainting via spatial projections

SS Phutke, S Murala - Pattern Recognition, 2023 - Elsevier
Image inpainting is now-a-days sought after due to its wide variety of applications in the
reconstruction of the corrupted image, occlusion removal, reflection removal, etc. Existing …

Art Image Inpainting with Style-guided Dual-branch Inpainting Network

Q Wang, Z Wang, X Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Traditionally, art images have to be restored by professionals for a very long time. It is also
possible to maintain the artistic value of damaged art images by digitizing them and …

Bips: Bi-modal indoor panorama synthesis via residual depth-aided adversarial learning

C Oh, W Cho, Y Chae, D Park, L Wang… - European Conference on …, 2022 - Springer
Providing omnidirectional depth along with RGB information is important for numerous
applications. However, as omnidirectional RGB-D data is not always available, synthesizing …