Related papers: Bridging Information Asymmetry: A Hierarchical Fra…

Synthesizing medical images while preserving their structural information is crucial in medical research. In such scenarios, the preservation of anatomical content becomes especially important. Although recent advances have been made by…

Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric prior while high-quality…

Blind face restoration is a highly ill-posed problem due to the lack of necessary context. Although existing methods produce high-quality outputs, they often fail to faithfully preserve the individual's identity. In this paper, we propose a…

Human mesh recovery (HMR) from a single RGB image is inherently ambiguous, as multiple 3D poses can correspond to the same 2D observation. Recent diffusion-based methods tackle this by generating various hypotheses, but often sacrifice…

The information bottleneck framework provides a systematic approach to learning representations that compress nuisance information in the input and extract semantically meaningful information about predictions. However, the choice of a…

With the increasing deployment of facial image data across a wide range of applications, efficient compression tailored to facial semantics has become critical for both storage and transmission. While recent learning-based face image…

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…

Expansion-enhanced sparse lexical representation improves information retrieval (IR) by minimizing vocabulary mismatch problems during lexical matching. In this paper, we explore the potential of jointly learning dense semantic…

Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including…

Vision foundation models pre-trained on massive data encode rich representations of real-world concepts, which can be adapted to downstream tasks by fine-tuning. However, fine-tuning foundation models on one task often leads to the issue of…

Blind image restoration is a non-convex problem which involves restoration of images from an unknown blur kernel. The factors affecting the performance of this restoration are how much prior information about an image and a blur kernel are…

In image restoration, single-step discriminative mappings often lack fine details via expectation learning, whereas generative paradigms suffer from inefficient multi-step sampling and noise-residual coupling. To address this dilemma, we…

Feature selection eliminates redundancy among features to improve downstream task performance while reducing computational overhead. Existing methods often struggle to capture intricate feature interactions and adapt across diverse…

Purpose: To investigate whether a vision-language foundation model can enhance undersampled MRI reconstruction by providing high-level contextual information beyond conventional priors. Methods: We proposed a semantic distribution-guided…

Perceptual image restoration seeks for high-fidelity images that most likely degrade to given images. For better visual quality, previous work proposed to search for solutions within the natural image manifold, by exploiting the latent…

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…

Realistic image restoration is a crucial task in computer vision, and diffusion-based models for image restoration have garnered significant attention due to their ability to produce realistic results. Restoration can be seen as a…

Pre-trained Vision-Language Models (VLMs) require Continual Learning (CL) to efficiently update their knowledge and adapt to various downstream tasks without retraining from scratch. However, for VLMs, in addition to the loss of knowledge…

Feature selection is a prevalent data preprocessing paradigm for various learning tasks. Due to the expensive cost of acquiring supervision information, unsupervised feature selection sparks great interests recently. However, existing…

Blind face restoration is a highly ill-posed problem that often requires auxiliary guidance to 1) improve the mapping from degraded inputs to desired outputs, or 2) complement high-quality details lost in the inputs. In this paper, we…