Image-to-Image

MOWA is a multiple-in-one image warping model that can be used for various tasks such as rectangling panoramic images, unrolling shutter images, rotating images, fisheye images, and image retargeting.

[ControlNet++] can improve image generation by ensuring that generated images match the given controls, like segmentation masks and depth maps. It shows better performance than its predecessor, ControlNet, with improvements of 7.9% in mIoU, 13.4% in SSIM, and 7.6% in RMSE.

ID2Reflectance can generate high-quality facial reflectance maps from a single image.

Desigen can generate high-quality design templates, including background images and layout elements. It uses advanced diffusion models for better control and has been tested on over 40,000 advertisement banners, achieving results similar to human designers.

Intrinsic Image Diffusion can generate detailed albedo, roughness, and metallic maps from a single indoor scene image.

AnimeInbet is a method that is able to generate inbetween frames for cartoon line drawings. Seeing this, we’ll hopefully be blessed with higher framerate animes in the near future.

[Total Selfie] can generate high-quality full-body selfies from close-up selfies and background images. It uses a diffusion-based approach to combine these inputs, creating realistic images in desired poses and overcoming the limits of traditional selfies.

Scenimefy can turn real-world images and videos into high-quality anime scenes. It uses a smart method that keeps important details and produces better results than other tools.

Interpolating between Images with Diffusion Models can generate smooth transitions between two images using latent diffusion models. It allows for high-quality results across different styles and subjects while using CLIP to select the best images for interpolation.

CSD-Edit is a multi modality editing approach that compared to other methods works great on images bigger than the traditional 512x512 limitation and can edit 4k or large panorama images, has improved temporal consistency on video frames as well as improved view consistency when editing or generating 3D scenes.

Ray Conditioning is a lightweight and geometry-free technique for multi-view image generation. You have that perfect portrait shot of a face but the angle is not right? No problem, just use that shot as an input image and generate the portrait from a another angle. Done.

Pix2Pix-Zero can edit images by changing them in real-time, like turning a cat into a dog, without needing extra text prompts or training. It keeps the original image’s structure and uses pre-trained text-to-image diffusion models for better editing results.

SDEdit can generate and edit photo-realistic images using user-guided inputs like hand-drawn strokes or text prompts. It outperforms GAN-based methods, achieving high scores in realism and overall satisfaction without needing specific training.