Related papers: Encoder-based Domain Tuning for Fast Personalizati…
We propose a novel approach for multi-modal Image-to-image (I2I) translation. To tackle the one-to-many relationship between input and output domains, previous works use complex training objectives to learn a latent embedding, jointly with…
Text-to-image (T2I) diffusion models have shown significant success in personalized text-to-image generation, which aims to generate novel images with human identities indicated by the reference images. Despite promising identity fidelity…
The personalized text-to-image generation has rapidly advanced with the emergence of Stable Diffusion. Existing methods, which typically fine-tune models using embedded identifiers, often struggle with insufficient stylization and…
Personalized retrieval and segmentation aim to locate specific instances within a dataset based on an input image and a short description of the reference instance. While supervised methods are effective, they require extensive labeled data…
Unsupervised multi-domain image-to-image translation aims to synthesis images among multiple domains without labeled data, which is more general and complicated than one-to-one image mapping. However, existing methods mainly focus on…
Visual concept personalization aims to transfer only specific image attributes, such as identity, expression, lighting, and style, into unseen contexts. However, existing methods rely on holistic embeddings from general-purpose image…
Tuning-free face personalization methods have developed along two distinct paradigms: text embedding approaches that map facial features into the text embedding space, and adapter-based methods that inject features through auxiliary…
Face personalization aims to insert specific faces, taken from images, into pretrained text-to-image diffusion models. However, it is still challenging for previous methods to preserve both the identity similarity and editability due to…
Domain adaptation refers to the process of learning prediction models in a target domain by making use of data from a source domain. Many classic methods solve the domain adaptation problem by establishing a common latent space, which may…
Since annotating pixel-level labels for semantic segmentation is laborious, leveraging synthetic data is an attractive solution. However, due to the domain gap between synthetic domain and real domain, it is challenging for a model trained…
Diffusion models have shown remarkable performance in image synthesis, but they demand extensive computational and memory resources for training, fine-tuning and inference. Although advanced quantization techniques have successfully…
Recent text-to-image personalization methods have shown great promise in teaching a diffusion model user-specified concepts given a few images for reusing the acquired concepts in a novel context. With massive efforts being dedicated to…
Many real-world datasets can be divided into groups according to certain salient features (e.g. grouping images by subject, grouping text by font, etc.). Often, machine learning tasks require that these features be represented separately…
Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…
This paper explores the possibility of learning custom tokens for representing new concepts in Vision-Language Models (VLMs). Our aim is to learn tokens that can be effective for both discriminative and generative tasks while composing well…
Generative models have made significant progress in the tasks of modeling complex data distributions such as natural images. The introduction of Generative Adversarial Networks (GANs) and auto-encoders lead to the possibility of training on…
Text-to-image (T2I) diffusion models, when fine-tuned on a few personal images, can generate visuals with a high degree of consistency. However, such fine-tuned models are not robust; they often fail to compose with concepts of pretrained…
Text-to-Image Diffusion Models such as Stable-Diffusion and Imagen have achieved unprecedented quality of photorealism with state-of-the-art FID scores on MS-COCO and other generation benchmarks. Given a caption, image generation requires…
Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with…
Personalized image generation via text prompts has great potential to improve daily life and professional work by facilitating the creation of customized visual content. The aim of image personalization is to create images based on a…