Related papers: DiffInf: Influence-Guided Diffusion for Supervisio…
Facial analysis models are increasingly applied in real-world applications that have significant impact on peoples' lives. However, as literature has shown, models that automatically classify facial attributes might exhibit algorithmic…
Face anonymization aims to conceal identity information while preserving non-identity attributes. Mainstream diffusion models rely on inference-time interventions such as negative guidance or energy-based optimization, which are applied…
As one of the most successful generative models, diffusion models have demonstrated remarkable efficacy in synthesizing high-quality images. These models learn the underlying high-dimensional data distribution in an unsupervised manner.…
Point supervision has become a scalable solution to address dense annotation for infrared small target detection, but its performance is limited by two coupled bottlenecks: unstable pseudo-label evolution in cluttered, low-contrast infrared…
Diffusion models have demonstrated remarkable progress in image generation quality, especially when guidance is used to control the generative process. However, guidance requires a large amount of image-annotation pairs for training and is…
Facial attribute editing and style manipulation are crucial for applications like virtual avatars and photo editing. However, achieving precise control over facial attributes without altering unrelated features is challenging due to the…
Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining. That is why guidance was harnessed from self-supervised learning backbones, like…
In latest years plethora of identity-preserving adapters for a personalized generation with diffusion models have been released. Their main disadvantage is that they are dominantly trained jointly with base diffusion models, which suffer…
The domain diversities including inconsistent annotation and varied image collection conditions inevitably exist among different facial expression recognition (FER) datasets, which pose an evident challenge for adapting the FER model…
Old-photo face restoration poses significant challenges due to compounded degradations such as breakage, fading, and severe blur. Existing pre-trained diffusion-guided methods either rely on explicit degradation priors or global statistical…
In this paper, we propose a diffusion-based face swapping framework for the first time, called DiffFace, composed of training ID conditional DDPM, sampling with facial guidance, and a target-preserving blending. In specific, in the training…
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…
Facial attribute editing aims to modify target attributes while preserving attribute-irrelevant content and overall image fidelity. Existing GAN-based methods provide favorable controllability, but often suffer from weak alignment between…
Data plays a pivotal role in the groundbreaking advancements in artificial intelligence. The quantitative analysis of data significantly contributes to model training, enhancing both the efficiency and quality of data utilization. However,…
Diffusion models conditioned on identity embeddings enable the generation of synthetic face images that consistently preserve identity across multiple samples. Recent work has shown that introducing an additional negative condition through…
Training deep neural networks is challenging when large and annotated datasets are unavailable. Extensive manual annotation of data samples is time-consuming, expensive, and error-prone, notably when it needs to be done by experts. To…
Diffusion and flow-based models have enabled significant progress in generation tasks across various modalities and have recently found applications in predictive learning. However, unlike typical generation tasks that encourage sample…
In the personalization process of large-scale text-to-image models, overfitting often occurs when learning specific subject from a limited number of images. Existing methods, such as DreamBooth, mitigate this issue through a class-specific…
We introduce GANDiff FR, the first synthetic framework that precisely controls demographic and environmental factors to measure, explain, and reduce bias with reproducible rigor. GANDiff FR unifies StyleGAN3-based identity-preserving…
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…