Related papers: DreamRelation: Bridging Customization and Relation…
Personalizing text-to-image diffusion models involves integrating novel visual concepts from a small set of reference images while retaining the model's original generative capabilities. However, this process often leads to overfitting,…
Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge.…
Incorporating a customized object into image generation presents an attractive feature in text-to-image generation. However, existing optimization-based and encoder-based methods are hindered by drawbacks such as time-consuming…
Intelligent robots require object-level scene understanding to reason about possible tasks and interactions with the environment. Moreover, many perception tasks such as scene reconstruction, image retrieval, or place recognition can…
Large-scale text-to-image generative models have been a ground-breaking development in generative AI, with diffusion models showing their astounding ability to synthesize convincing images following an input text prompt. The goal of image…
Personalized text-to-image (T2I) generation has emerged as a key application for creating user-specific concepts from a few reference images. The core challenge is concept disentanglement: separating the target concept from irrelevant…
Recent advancements in generative models have significantly facilitated the development of personalized content creation. Given a small set of images with user-specific concept, personalized image generation allows to create images that…
Multi-subject personalized image generation aims to synthesize customized images containing multiple specified subjects without requiring test-time optimization. However, achieving fine-grained independent control over multiple subjects…
Diffusion models have demonstrated their capability to synthesize high-quality and diverse images from textual prompts. However, simultaneous control over both global contexts (e.g., object layouts and interactions) and local details (e.g.,…
The popularization of Text-to-Image (T2I) diffusion models enables the generation of high-quality images from text descriptions. However, generating diverse customized images with reference visual attributes remains challenging. This work…
Image captioning is a longstanding problem in the field of computer vision and natural language processing. To date, researchers have produced impressive state-of-the-art performance in the age of deep learning. Most of these…
Recent works demonstrate a remarkable ability to customize text-to-image diffusion models while only providing a few example images. What happens if you try to customize such models using multiple, fine-grained concepts in a sequential…
We present BootComp, a novel framework based on text-to-image diffusion models for controllable human image generation with multiple reference garments. Here, the main bottleneck is data acquisition for training: collecting a large-scale…
Person re-identification (re-ID) models trained on one domain often fail to generalize well to another. In our attempt, we present a "learning via translation" framework. In the baseline, we translate the labeled images from source to…
Despite recent progress, text-to-image models still struggle to generate semantically diverse and compositionally accurate multi-person interaction scenes, often collapsing to repetitive layouts, stereotypical poses, and poorly grounded…
Deep generative models come with the promise to learn an explainable representation for visual objects that allows image sampling, synthesis, and selective modification. The main challenge is to learn to properly model the independent…
Personalized image generation with text-to-image diffusion models generates unseen images based on reference image content. Zero-shot adapter methods such as IP-Adapter and OminiControl are especially interesting because they do not require…
With the recent advancement in deep learning, we have witnessed a great progress in single image super-resolution. However, due to the significant information loss of the image downscaling process, it has become extremely challenging to…
Person re-identification (re-ID) aims at matching images of the same identity across camera views. Due to varying distances between cameras and persons of interest, resolution mismatch can be expected, which would degrade person re-ID…
Personalizing diffusion models to specific users or concepts remains challenging, particularly when only a few reference images are available. Existing methods such as DreamBooth and Textual Inversion often overfit to limited data, causing…