Search Results for author:
Found 39 papers, 13 papers with code
CLIPasso: Semantically-Aware Object Sketching
Abstraction is at the heart of sketching due to the simple and minimal nature of line drawings.
Deep motifs and motion signatures
In this paper we introduce motion motifs and motion signatures that are a succinct but descriptive representation of motion sequences.
Deep Online Video Stabilization
In this paper, we solve the video stabilization problem using a convolutional neural network (ConvNet).
Graphics
Learned Queries for Efficient Local Attention
Vision Transformers (ViT) serve as powerful vision models.
Ranked #362 on
Image Classification
on ImageNet
Semantify: Simplifying the Control of 3D Morphable Models using CLIP
We present Semantify: a self-supervised method that utilizes the semantic power of CLIP language-vision foundation model to simplify the control of 3D morphable models.
Semantic Segmentation in Art Paintings
In this paper, we tackle the problem of semantic segmentation of artistic paintings, an even more challenging task because of a much larger diversity in colors, textures, and shapes and because there are no ground truth annotations available for segmentation.
Predictive and Generative Neural Networks for Object Functionality
Given a 3D object in isolation, our functional similarity network (fSIM-NET), a variation of the triplet network, is trained to predict the functionality of the object by inferring functionality-revealing interaction contexts.
CAST: Character labeling in Animation using Self-supervision by Tracking
Using this space we can build dictionaries of characters in an animation videos, and define specialized classifiers for specific stylistic content (e. g., characters in a specific animation series) with very little user effort.
InAugment: Improving Classifiers via Internal Augmentation
Image augmentation techniques apply transformation functions such as rotation, shearing, or color distortion on an input image.
ARO-Net: Learning Implicit Fields from Anchored Radial Observations
We introduce anchored radial observations (ARO), a novel shape encoding for learning implicit field representation of 3D shapes that is category-agnostic and generalizable amid significant shape variations.
SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction
Sketching is a powerful tool for creating abstract images that are sparse but meaningful.
Neural Font Rendering
Recent advances in deep learning techniques and applications have revolutionized artistic creation and manipulation in many domains (text, images, music); however, fonts have not yet been integrated with deep learning architectures in a manner that supports their multi-scale nature.
VCR: Video representation for Contextual Retrieval
Streamlining content discovery within media archives requires integrating advanced data representations and effective visualization techniques for clear communication of video topics to users.
Image Resizing by Reconstruction from Deep Features
In this paper we perform image resizing in feature space where the deep layers of a neural network contain rich important semantic information.
On the Role of Geometry in Geo-Localization
We find that the network is capable of estimating the camera pose from the lean images, and it does so not by memorization but by some measure of geometric learning of the geographical area.
GRAINS: Generative Recursive Autoencoders for INdoor Scenes
We present a generative neural network which enables us to generate plausible 3D indoor scenes in large quantities and varieties, easily and highly efficiently.
Graphics
Deep Portrait Image Completion and Extrapolation
We evaluate our method on public portrait image datasets, and show that it outperforms other state-of-art general image completion methods.
Graphics
Focus-and-Expand: Training Guidance Through Gradual Manipulation of Input Features
Drawing inspiration from Parameter Continuation methods, we propose steering the training process to consider specific features in the input more than others, through gradual shifts in the input domain.
NPRportrait 1.0: A Three-Level Benchmark for Non-Photorealistic Rendering of Portraits
Despite the recent upsurge of activity in image-based non-photorealistic rendering (NPR), and in particular portrait image stylisation, due to the advent of neural style transfer, the state of performance evaluation in this field is limited, especially compared to the norms in the computer vision and machine learning communities.
Neural Alignment for Face De-pixelization
Although simple, our framework synthesizes high-quality face reconstructions, demonstrating that given the statistical prior of a human face, multiple aligned pixelated frames contain sufficient information to reconstruct a high-quality approximation of the original signal.
Ordered Attention for Coherent Visual Storytelling
OIA models interactions between the sentence-corresponding image and important regions in other images of the sequence.
Sketch2Photo: Internet Image Montage
The composed picture is generated by seamlessly stitching several photographs in agreement with the sketch and text labels; these are found by searching the Internet.
Deep Symmetric Network for Underexposed Image Enhancement With Recurrent Attentional Learning
Underexposed image enhancement is of importance in many research domains.
Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure
In this work, we present a music-driven motion synthesis framework that generates long-term sequences of human motions which are synchronized with the input beats, and jointly form a global structure that respects a specific dance genre.
Lean Images for Geo-Localization
In this paper we consider the geo-localization task - finding the pose of a camera in a large 3D scene from a single lean image, i. e. an image with no texture.
How Low Can We Go? Pixel Annotation for Semantic Segmentation
Based on this single-image-annotation experiment, we design an experiment to quickly annotate an entire data set.
DeepPortraitDrawing: Generating Human Body Images from Freehand Sketches
Researchers have explored various ways to generate realistic images from freehand sketches, e. g., for objects and human faces.
CLIPascene: Scene Sketching with Different Types and Levels of Abstraction
In this paper, we present a method for converting a given scene image into a sketch using different types and multiple levels of abstraction.
Prediction of Scene Plausibility
Understanding the 3D world from 2D images involves more than detection and segmentation of the objects within the scene.
PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data
In this work, we propose an approach to leverage synthetic scene data for improving video understanding.
Word-As-Image for Semantic Typography
A word-as-image is a semantic typography technique where a word illustration presents a visualization of the meaning of the word, while also preserving its readability.
PersonalTailor: Personalizing 2D Pattern Design from 3D Garment Point Clouds
Garment pattern design aims to convert a 3D garment to the corresponding 2D panels and their sewing structure.
Concept Decomposition for Visual Exploration and Inspiration
Each node in the tree represents a sub-concept using a learned vector embedding injected into the latent space of a pretrained text-to-image model.
HoughLaneNet: Lane Detection with Deep Hough Transform and Dynamic Convolution
By utilizing the lane features in the Hough parameter space, the network learns dynamic convolution kernel parameters corresponding to each lane, allowing the Dynamic Convolution Module to effectively differentiate between lane features.
Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models
Text-to-image (T2I) personalization allows users to guide the creative image generation process by combining their own visual concepts in natural language prompts.
Breathing Life Into Sketches Using Text-to-Video Priors
A sketch is one of the most intuitive and versatile tools humans use to convey their ideas visually.
PALP: Prompt Aligned Personalization of Text-to-Image Models
We term our approach prompt-aligned personalization.
FontCLIP: A Semantic Typography Visual-Language Model for Multilingual Font Applications
To solve this problem, we present FontCLIP: a model that connects the semantic understanding of a large vision-language model with typographical knowledge.
Implicit Style-Content Separation using B-LoRA
In this paper, we introduce B-LoRA, a method that leverages LoRA (Low-Rank Adaptation) to implicitly separate the style and content components of a single image, facilitating various image stylization tasks.
