Search Results for author:
Found 33 papers, 20 papers with code
REED-VAE: RE-Encode Decode Training for Iterative Image Editing with Diffusion Models
While latent diffusion models achieve impressive image editing results, their application to iterative editing of the same image is severely restricted.
ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation
To address this challenge, we explore the usage of Retrieval-Augmented Generation (RAG) with image generation models.
Tiled Diffusion
This paper presents Tiled Diffusion, a novel approach that extends the capabilities of diffusion models to accommodate the generation of cohesive tiling patterns across various domains of image synthesis that require tiling.
Memories of Forgotten Concepts
Diffusion models dominate the space of text-to-image generation, yet they may produce undesirable outputs, including explicit content or private data.
Stable Flow: Vital Layers for Training-Free Image Editing
The main challenge is that, unlike the UNet-based models, DiT lacks a coarse-to-fine synthesis structure, making it unclear in which layers to perform the injection.
Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation
While these models have been used to generate training data for classification tasks, their effectiveness in full-dataset training of FGVC models remains under-explored.
Ranked #1 on
Few-Shot Learning
on DTD
V-LASIK: Consistent Glasses-Removal from Videos Using Synthetic Data
We show that despite data imperfection, by learning from our generated data and leveraging the prior of pretrained diffusion models, our model is able to perform the desired edit consistently while preserving the original video content.
Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer
Given the remarkable results of motion synthesis with diffusion models, a natural question arises: how can we effectively leverage these models for motion editing?
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.
Diffusing Colors: Image Colorization with Text Guided Diffusion
To tackle these issues, we present a novel image colorization framework that utilizes image diffusion techniques with granular text prompts.
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.
Differential Diffusion: Giving Each Pixel Its Strength
While current techniques enable user control over the degree of change in an image edit, the controllability is limited to global changes over an entire edited region.
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.
Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysis
Our method can detect images from a known generative model and enable us to establish relationships between fine-tuned generative models.
Prediction of Scene Plausibility
Understanding the 3D world from 2D images involves more than detection and segmentation of the objects within the scene.
FakeOut: Leveraging Out-of-domain Self-supervision for Multi-modal Video Deepfake Detection
This poses a problem, especially in the era of social media, as synthetic videos of speaking humans can be used to spread misinformation in a convincing manner.
Taming Normalizing Flows
We propose an algorithm for taming Normalizing Flow models - changing the probability that the model will produce a specific image or image category.
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.
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.
GEFF: Improving Any Clothes-Changing Person ReID Model using Gallery Enrichment with Face Features
Combined with the latest ReID models, our method achieves new SOTA results on the PRCC, LTCC, CCVID, LaST and VC-Clothes benchmarks and the proposed 42Street dataset.
Ranked #1 on
Person Re-Identification
on LTCC
Ham2Pose: Animating Sign Language Notation into Pose Sequences
Additionally, we offer a new distance measurement that considers missing keypoints, to measure the distance between pose sequences using DTW-MJE.
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.
DDNeRF: Depth Distribution Neural Radiance Fields
We present depth distribution neural radiance field (DDNeRF), a new method that significantly increases sampling efficiency along rays during training while achieving superior results for a given sampling budget.
Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images
Our model can disentangle the geometry and appearance variations in the scene, i. e., we can independently sample from the geometry and appearance spaces of the generative model.
DeepShadow: Neural Shape from Shadow
We show that the self and cast shadows not only do not disturb 3D reconstruction, but can be used alone, as a strong learning signal, to recover the depth map and surface normals.
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
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.
Endless Loops: Detecting and Animating Periodic Patterns in Still Images
We present an algorithm for producing a seamless animated loop from a single image.
Iterative Text-based Editing of Talking-heads Using Neural Retargeting
We present a text-based tool for editing talking-head video that enables an iterative editing workflow.
State of the Art on Neural Rendering
Neural rendering is a new and rapidly emerging field that combines generative machine learning techniques with physical knowledge from computer graphics, e. g., by the integration of differentiable rendering into network training.
Lifespan Age Transformation Synthesis
Most existing aging methods are limited to changing the texture, overlooking transformations in head shape that occur during the human aging and growth process.
Text-based Editing of Talking-head Video
To edit a video, the user has to only edit the transcript, and an optimization strategy then chooses segments of the input corpus as base material.
Finding Distractors In Images
We propose a new computer vision task we call "distractor prediction."
