We present Semantify: a self-supervised method that utilizes the semanti...
Text-to-image (T2I) personalization allows users to guide the creative i...
The task of lane detection has garnered considerable attention in the fi...
A creative idea is often born from transforming, combining, and modifyin...
We present a technique to optimize the reflectivity of a surface while
p...
Garment pattern design aims to convert a 3D garment to the corresponding...
A word-as-image is a semantic typography technique where a word illustra...
Action recognition models have achieved impressive results by incorporat...
Understanding the 3D world from 2D images involves more than detection a...
In this paper, we present a method for converting a given scene image in...
Recent advances in deep learning techniques and applications have
revolu...
Semantic segmentation is a difficult task even when trained in a supervi...
Abstraction is at the heart of sketching due to the simple and minimal n...
How many labeled pixels are needed to segment an image, without any prio...
Cartoons and animation domain videos have very different characteristics...
Vision Transformers (ViT) serve as powerful vision models. Unlike
convol...
Synthesizing human motion with a global structure, such as a choreograph...
We address the problem of visual storytelling, i.e., generating a story ...
Image augmentation techniques apply transformation functions such as
rot...
We present a simple method to reconstruct a high-resolution video from a...
Despite the recent upsurge of activity in image-based non-photorealistic...
We present a simple and intuitive Focus-and-eXpand () method to guide th...
Humans can build a mental map of a geographical area to find their way a...
Traditional image resizing methods usually work in pixel space and use
v...
We present the first algorithm for designing volumetric Michell Trusses....
General image completion and extrapolation methods often fail on portrai...
We present a generative neural network which enables us to generate plau...
Video stabilization technique is essential for most hand-held captured v...
ThreadTone is an NPR representation of an input image by half-toning usi...