Related papers: PFStorer: Personalized Face Restoration and Super-…
The latest developments in Face Restoration have yielded significant advancements in visual quality through the utilization of diverse diffusion priors. Nevertheless, the uncertainty of face identity introduced by identity-obscure inputs…
Human-centric generative models designed for AI-driven storytelling must bring together two core capabilities: identity consistency and precise control over human performance. While recent diffusion-based approaches have made significant…
Following the remarkable success of diffusion models on image generation, recent works have also demonstrated their impressive ability to address a number of inverse problems in an unsupervised way, by properly constraining the sampling…
Image retouching aims to enhance the visual quality of photos. Considering the different aesthetic preferences of users, the target of retouching is subjective. However, current retouching methods mostly adopt deterministic models, which…
Although diffusion models are rising as a powerful solution for blind face restoration, they are criticized for two problems: 1) slow training and inference speed, and 2) failure in preserving identity and recovering fine-grained facial…
In recent years, the role of image generative models in facial reenactment has been steadily increasing. Such models are usually subject-agnostic and trained on domain-wide datasets. The appearance of the reenacted individual is learned…
Diffusion models have demonstrated remarkable efficacy in generating high-quality samples. Existing diffusion-based image restoration algorithms exploit pre-trained diffusion models to leverage data priors, yet they still preserve elements…
Face stylization refers to the transformation of a face into a specific portrait style. However, current methods require the use of example-based adaptation approaches to fine-tune pre-trained generative models so that they demand lots of…
Blind face restoration has made great progress in producing high-quality and lifelike images. Yet it remains challenging to preserve the ID information especially when the degradation is heavy. Current reference-guided face restoration…
Face restoration has achieved remarkable advancements through the years of development. However, ensuring that restored facial images exhibit high fidelity, preserve authentic features, and avoid introducing artifacts or biases remains a…
Human body restoration plays a vital role in various applications related to the human body. Despite recent advances in general image restoration using generative models, their performance in human body restoration remains mediocre, often…
Existing diffusion models show great potential for identity-preserving generation. However, personalized portrait generation remains challenging due to the diversity in user profiles, including variations in appearance and lighting…
Recent advancements in personalized image generation using diffusion models have been noteworthy. However, existing methods suffer from inefficiencies due to the requirement for subject-specific fine-tuning. This computationally intensive…
Blind face restoration is a challenging task due to the unknown and complex degradation. Although face prior-based methods and reference-based methods have recently demonstrated high-quality results, the restored images tend to contain…
The inherent generative power of denoising diffusion models makes them well-suited for image restoration tasks where the objective is to find the optimal high-quality image within the generative space that closely resembles the input image.…
The rapid growth of social media has led to the widespread sharing of individual portrait images, which pose serious privacy risks due to the capabilities of automatic face recognition (AFR) systems for mass surveillance. Hence, protecting…
Personalized image synthesis has emerged as a pivotal application in text-to-image generation, enabling the creation of images featuring specific subjects in diverse contexts. While diffusion models have dominated this domain,…
Modern cameras' performance in low-light conditions remains suboptimal due to fundamental limitations in photon shot noise and sensor read noise. Generative image restoration methods have shown promising results compared to traditional…
Portrait pictures, which typically feature both human subjects and natural backgrounds, are one of the most prevalent forms of photography on social media. Existing image super-resolution (ISR) techniques generally focus either on generic…
In human-centric content generation, the pre-trained text-to-image models struggle to produce user-wanted portrait images, which retain the identity of individuals while exhibiting diverse expressions. This paper introduces our efforts…