Related papers: Dual Variational Generation for Low-Shot Heterogen…
The advent of Generative Adversarial Networks (GANs) has brought about completely novel ways of transforming and manipulating pixels in digital images. GAN based techniques such as Image-to-Image translations, DeepFakes, and other automated…
Blind face restoration (BFR) is important while challenging. Prior works prefer to exploit GAN-based frameworks to tackle this task due to the balance of quality and efficiency. However, these methods suffer from poor stability and…
The large domain discrepancy between faces captured in polarimetric (or conventional) thermal and visible domain makes cross-domain face recognition quite a challenging problem for both human-examiners and computer vision algorithms.…
Occlusion is a common problem with biometric recognition in the wild. The generalization ability of CNNs greatly decreases due to the adverse effects of various occlusions. To this end, we propose a novel unified framework integrating the…
High Dynamic Range (HDR) imaging aims to generate an artifact-free HDR image with realistic details by fusing multi-exposure Low Dynamic Range (LDR) images. Caused by large motion and severe under-/over-exposure among input LDR images, HDR…
Image super-resolution (SR) methods essentially lead to a loss of some high-frequency (HF) information when predicting high-resolution (HR) images from low-resolution (LR) images without using external references. To address this issue, we…
Recent advances in domain adaptation, especially those applied to heterogeneous facial recognition, typically rely upon restrictive Euclidean loss functions (e.g., $L_2$ norm) which perform best when images from two different domains (e.g.,…
While diffusion models dominate the field of visual generation, they are computationally inefficient, applying a uniform computational effort regardless of different complexity. In contrast, autoregressive (AR) models are inherently…
Retrieving videos of a particular person with face image as a query via hashing technique has many important applications. While face images are typically represented as vectors in Euclidean space, characterizing face videos with some…
Recognition of low-quality face images remains a challenge due to invisible or deformation in partial facial regions. For low-quality images dominated by missing partial facial regions, local region similarity contributes more to face…
Modern deep neural networks struggle to transfer knowledge and generalize across diverse domains when deployed to real-world applications. Currently, domain generalization (DG) is introduced to learn a universal representation from multiple…
Graph Neural Networks (GNNs) have excelled in handling graph-structured data, attracting significant research interest. However, two primary challenges have emerged: interference between topology and attributes distorting node…
High dynamic range (HDR) imaging is an indispensable technique in modern photography. Traditional methods focus on HDR reconstruction from multiple images, solving the core problems of image alignment, fusion, and tone mapping, yet having a…
Training-free high-resolution (HR) image generation has garnered significant attention due to the high costs of training large diffusion models. Most existing methods begin by reconstructing the overall structure and then proceed to refine…
We present a novel generative modeling framework,Wavelet-Fourier-Diffusion, which adapts the diffusion paradigm to hybrid frequency representations in order to synthesize high-quality, high-fidelity images with improved spatial…
The inherent difficulty in acquiring accurately co-registered RGB-hyperspectral image (HSI) pairs has significantly impeded the practical deployment of current data-driven Hyperspectral Image Generation (HIG) networks in engineering…
In recent years, Multi-View Clustering (MVC) has been significantly advanced under the influence of deep learning. By integrating heterogeneous data from multiple views, MVC enhances clustering analysis, making multi-view fusion critical to…
Photorealistic frontal view synthesis from a single face image has a wide range of applications in the field of face recognition. Although data-driven deep learning methods have been proposed to address this problem by seeking solutions…
Received waveforms contain rich information for both range information and environment semantics. However, its full potential is hard to exploit under multipath and non-line-of-sight conditions. This paper proposes a deep generative model…
Age estimation from facial images is typically cast as a label distribution learning or regression problem, since aging is a gradual progress. Its main challenge is the facial feature space w.r.t. ages is inhomogeneous, due to the large…