Search Results for author:
Found 50 papers, 25 papers with code
Cross-Domain Cascaded Deep Translation
We mitigate this by descending the deep layers of a pre-trained network, where the deep features contain more semantics, and applying the translation between these deep features.
Click2Mask: Local Editing with Dynamic Mask Generation
Recent advancements in generative models have revolutionized image generation and editing, making these tasks accessible to non-experts.
Seed-to-Seed: Image Translation in Diffusion Seed Space
In contrast to existing methods that modify images during the diffusion sampling process, we leverage the semantic information encoded within the space of inverted seeds of a pretrained DM, dubbed as the seed-space.
DiffUHaul: A Training-Free Method for Object Dragging in Images
In this work, we propose a training-free method, dubbed DiffUHaul, that harnesses the spatial understanding of a localized text-to-image model, for the object dragging task.
EmoEdit: Evoking Emotions through Image Manipulation
We introduce EmoEdit, a novel two-stage framework comprising emotion attribution and image editing.
Generating Non-Stationary Textures using Self-Rectification
This paper addresses the challenge of example-based non-stationary texture synthesis.
Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment
While existing image-text alignment models reach high quality binary assessments, they fall short of pinpointing the exact source of misalignment.
S2ST: Image-to-Image Translation in the Seed Space of Latent Diffusion
Image-to-image translation (I2IT) refers to the process of transforming images from a source domain to a target domain while maintaining a fundamental connection in terms of image content.
The Chosen One: Consistent Characters in Text-to-Image Diffusion Models
Recent advances in text-to-image generation models have unlocked vast potential for visual creativity.
Noise-Free Score Distillation
Score Distillation Sampling (SDS) has emerged as the de facto approach for text-to-content generation in non-image domains.
EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes
Most of the existing work in this area focuses on feature design, while little attention has been paid to dataset construction.
SVNR: Spatially-variant Noise Removal with Denoising Diffusion
Our formulation also accounts for the correlation that exists between the condition image and the samples along the modified diffusion process.
Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields
We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts, along with a 3D ROI box.
Chatting Makes Perfect: Chat-based Image Retrieval
These questions form a dialog with the user in order to retrieve the desired image from a large corpus.
Break-A-Scene: Extracting Multiple Concepts from a Single Image
Text-to-image model personalization aims to introduce a user-provided concept to the model, allowing its synthesis in diverse contexts.
Data Roaming and Quality Assessment for Composed Image Retrieval
To address these shortcomings, we introduce the Large Scale Composed Image Retrieval (LaSCo) dataset, a new CoIR dataset which is ten times larger than existing ones.
Ranked #1 on
Image Retrieval
on LaSCo
SpaText: Spatio-Textual Representation for Controllable Image Generation
Due to lack of large-scale datasets that have a detailed textual description for each region in the image, we choose to leverage the current large-scale text-to-image datasets and base our approach on a novel CLIP-based spatio-textual representation, and show its effectiveness on two state-of-the-art diffusion models: pixel-based and latent-based.
What's in a Decade? Transforming Faces Through Time
How can one visually characterize people in a decade?
Blended Latent Diffusion
Our solution leverages a recent text-to-image Latent Diffusion Model (LDM), which speeds up diffusion by operating in a lower-dimensional latent space.
Shape-Pose Disentanglement using SE(3)-equivariant Vector Neurons
We introduce an unsupervised technique for encoding point clouds into a canonical shape representation, by disentangling shape and pose.
Multi-level Latent Space Structuring for Generative Control
Truncation is widely used in generative models for improving the quality of the generated samples, at the expense of reducing their diversity.
Third Time's the Charm? Image and Video Editing with StyleGAN3
In particular, we demonstrate that while StyleGAN3 can be trained on unaligned data, one can still use aligned data for training, without hindering the ability to generate unaligned imagery.
ShapeFormer: Transformer-based Shape Completion via Sparse Representation
We present ShapeFormer, a transformer-based network that produces a distribution of object completions, conditioned on incomplete, and possibly noisy, point clouds.
Classification-Regression for Chart Comprehension
Our model is particularly well suited for realistic questions with out-of-vocabulary answers that require regression.
Ranked #2 on
Visual Question Answering (VQA)
on PlotQA-D1
Blended Diffusion for Text-driven Editing of Natural Images
Natural language offers a highly intuitive interface for image editing.
text-guided-image-editing
Zero-Shot Text-to-Image Generation
StyleAlign: Analysis and Applications of Aligned StyleGAN Models
Several works already utilize some basic properties of aligned StyleGAN models to perform image-to-image translation.
ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation
The reason is that the learnt weights for balancing the importance between the shape and base components in ShapeConv become constants in the inference phase, and thus can be fused into the following convolution, resulting in a network that is identical to one with vanilla convolutional layers.
Ranked #3 on
Semantic Segmentation
on Stanford2D3D - RGBD
GAN Cocktail: mixing GANs without dataset access
In the second stage, we merge the rooted models by averaging their weights and fine-tuning them for each specific domain, using only data generated by the original trained models.
StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery
Inspired by the ability of StyleGAN to generate highly realistic images in a variety of domains, much recent work has focused on understanding how to use the latent spaces of StyleGAN to manipulate generated and real images.
Evaluation and Comparison of Edge-Preserving Filters
Edge-preserving filters play an essential role in some of the most basic tasks of computational photography, such as abstraction, tonemapping, detail enhancement and texture removal, to name a few.
StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation
Manipulation of visual attributes via these StyleSpace controls is shown to be better disentangled than via those proposed in previous works.
MotioNet: 3D Human Motion Reconstruction from Monocular Video with Skeleton Consistency
We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video. While previous methods rely on either rigging or inverse kinematics (IK) to associate a consistent skeleton with temporally coherent joint rotations, our method is the first data-driven approach that directly outputs a kinematic skeleton, which is a complete, commonly used, motion representation.
DO-Conv: Depthwise Over-parameterized Convolutional Layer
Moreover, in the inference phase, the depthwise convolution is folded into the conventional convolution, reducing the computation to be exactly equivalent to that of a convolutional layer without over-parameterization.
Skeleton-Aware Networks for Deep Motion Retargeting
In other words, our operators form the building blocks of a new deep motion processing framework that embeds the motion into a common latent space, shared by a collection of homeomorphic skeletons.
Unpaired Motion Style Transfer from Video to Animation
In this paper, we present a novel data-driven framework for motion style transfer, which learns from an unpaired collection of motions with style labels, and enables transferring motion styles not observed during training.
Unsupervised multi-modal Styled Content Generation
The emergence of deep generative models has recently enabled the automatic generation of massive amounts of graphical content, both in 2D and in 3D.
Illuminant Chromaticity Estimation from Interreflections
In this paper, we present a new, physically-based, approach for estimating illuminant chromaticity from interreflections of light between diffuse surfaces.
Cross-Domain Cascaded Deep Feature Translation
Our translation is performed in a cascaded, deep-to-shallow, fashion, along the deep feature hierarchy: we first translate between the deepest layers that encode the higher-level semantic content of the image, proceeding to translate the shallower layers, conditioned on the deeper ones.
Learning Character-Agnostic Motion for Motion Retargeting in 2D
In order to achieve our goal, we learn to extract, directly from a video, a high-level latent motion representation, which is invariant to the skeleton geometry and the camera view.
CrossNet: Latent Cross-Consistency for Unpaired Image Translation
Recent GAN-based architectures have been able to deliver impressive performance on the general task of image-to-image translation.
Multi-Scale Context Intertwining for Semantic Segmentation
Accurate semantic image segmentation requires the joint consideration of local appearance, semantic information, and global scene context.
Deep Video-Based Performance Cloning
After training a deep generative network using a reference video capturing the appearance and dynamics of a target actor, we are able to generate videos where this actor reenacts other performances.
Structure-aware Generative Network for 3D-Shape Modeling
The key idea is that during the analysis, the two branches exchange information between them, thereby learning the dependencies between structure and geometry and encoding two augmented features, which are then fused into a single latent code.
Graphics
DiDA: Disentangled Synthesis for Domain Adaptation
The key idea is that by learning to separately extract both the common and the domain-specific features, one can synthesize more target domain data with supervision, thereby boosting the domain adaptation performance.
Non-Stationary Texture Synthesis by Adversarial Expansion
We demonstrate that this conceptually simple approach is highly effective for capturing large-scale structures, as well as other non-stationary attributes of the input exemplar.
Neural Best-Buddies: Sparse Cross-Domain Correspondence
Correspondence between images is a fundamental problem in computer vision, with a variety of graphics applications.
Neuron-level Selective Context Aggregation for Scene Segmentation
Contextual information provides important cues for disambiguating visually similar pixels in scene segmentation.
Joint Bi-Layer Optimization for Single-Image Rain Streak Removal
A third prior is defined on the rain-streak layer R, based on similarity of patches to the extracted rain patches.
A Holistic Approach for Data-Driven Object Cutout
We show that the resulting P-maps may be used to evaluate how likely a rectangle proposal is to contain an instance of the class, and further process good proposals to produce an accurate object cutout mask.
Synthesizing Training Images for Boosting Human 3D Pose Estimation
Human 3D pose estimation from a single image is a challenging task with numerous applications.
