Moab Arar
YOU?
Author Swipe
View article: Diffusion Models Are Real-Time Game Engines
Diffusion Models Are Real-Time Game Engines Open
We present GameNGen, the first game engine powered entirely by a neural model that also enables real-time interaction with a complex environment over long trajectories at high quality. When trained on the classic game DOOM, GameNGen extrac…
View article: The Chosen One: Consistent Characters in Text-to-Image Diffusion Models
The Chosen One: Consistent Characters in Text-to-Image Diffusion Models Open
Recent advances in text-to-image generation models have unlocked vast potential for visual creativity. However, the users that use these models struggle with the generation of consistent characters, a crucial aspect for numerous real-world…
View article: PALP: Prompt Aligned Personalization of Text-to-Image Models
PALP: Prompt Aligned Personalization of Text-to-Image Models Open
Content creators often aim to create personalized images using personal subjects that go beyond the capabilities of conventional text-to-image models. Additionally, they may want the resulting image to encompass a specific location, style,…
View article: Curved Diffusion: A Generative Model With Optical Geometry Control
Curved Diffusion: A Generative Model With Optical Geometry Control Open
State-of-the-art diffusion models can generate highly realistic images based on various conditioning like text, segmentation, and depth. However, an essential aspect often overlooked is the specific camera geometry used during image captur…
View article: The Chosen One: Consistent Characters in Text-to-Image Diffusion Models
The Chosen One: Consistent Characters in Text-to-Image Diffusion Models Open
Recent advances in text-to-image generation models have unlocked vast potential for visual creativity. However, the users that use these models struggle with the generation of consistent characters, a crucial aspect for numerous real-world…
View article: Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models
Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models Open
Text-to-image (T2I) personalization allows users to guide the creative image generation process by combining their own visual concepts in natural language prompts. Recently, encoder-based techniques have emerged as a new effective approach…
View article: Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models
Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models Open
Text-to-image personalization aims to teach a pre-trained diffusion model to reason about novel, user provided concepts, embedding them into new scenes guided by natural language prompts. However, current personalization approaches struggl…
View article: Single Motion Diffusion
Single Motion Diffusion Open
Synthesizing realistic animations of humans, animals, and even imaginary creatures, has long been a goal for artists and computer graphics professionals. Compared to the imaging domain, which is rich with large available datasets, the numb…
View article: Learned Queries for Efficient Local Attention
Learned Queries for Efficient Local Attention Open
Vision Transformers (ViT) serve as powerful vision models. Unlike convolutional neural networks, which dominated vision research in previous years, vision transformers enjoy the ability to capture long-range dependencies in the data. Nonet…
View article: InAugment: Improving Classifiers via Internal Augmentation
InAugment: Improving Classifiers via Internal Augmentation Open
Image augmentation techniques apply transformation functions such as rotation, shearing, or color distortion on an input image. These augmentations were proven useful in improving neural networks' generalization ability. In this paper, we …
View article: Image resizing by reconstruction from deep features
Image resizing by reconstruction from deep features Open
Traditional image resizing methods usually work in pixel space and use various saliency measures. The challenge is to adjust the image shape while trying to preserve important content. In this paper we perform image resizing in feature spa…
View article: Focus-and-Expand: Training Guidance Through Gradual Manipulation of Input Features
Focus-and-Expand: Training Guidance Through Gradual Manipulation of Input Features Open
We present a simple and intuitive Focus-and-eXpand (\fax) method to guide the training process of a neural network towards a specific solution. Optimizing a neural network is a highly non-convex problem. Typically, the space of solutions i…
View article: Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation
Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation Open
Many applications, such as autonomous driving, heavily rely on multi-modal data where spatial alignment between the modalities is required. Most multi-modal registration methods struggle computing the spatial correspondence between the ima…
View article: Unsupervised Multi-Modal Image Registration via Geometry Preserving\n Image-to-Image Translation
Unsupervised Multi-Modal Image Registration via Geometry Preserving\n Image-to-Image Translation Open
Many applications, such as autonomous driving, heavily rely on multi-modal\ndata where spatial alignment between the modalities is required. Most\nmulti-modal registration methods struggle computing the spatial correspondence\nbetween the …
View article: Image Resizing by Reconstruction from Deep Features
Image Resizing by Reconstruction from Deep Features Open
Traditional image resizing methods usually work in pixel space and use various saliency measures. The challenge is to adjust the image shape while trying to preserve important content. In this paper we perform image resizing in feature spa…