Related papers: Adversarially-Refined VQ-GAN with Dense Motion Tok…

We propose in this paper a new paradigm for facial video compression. We leverage the generative capacity of GANs such as StyleGAN to represent and compress a video, including intra and inter compression. Each frame is inverted in the…

The rapid tracer kinetics of rubidium-82 ($^{82}$Rb) and high variation of cross-frame distribution in dynamic cardiac positron emission tomography (PET) raise significant challenges for inter-frame motion correction, particularly for the…

Generalization performance of trained computer vision systems that use computer graphics (CG) generated data is not yet effective due to the concept of 'domain-shift' between virtual and real data. Although simulated data augmented with a…

In image retrieval, deep local features learned in a data-driven manner have been demonstrated effective to improve retrieval performance. To realize efficient retrieval on large image database, some approaches quantize deep local features…

Human motion capture data has been widely used in data-driven character animation. In order to generate realistic, natural-looking motions, most data-driven approaches require considerable efforts of pre-processing, including motion…

Vision language models (VLMs) excel in multimodal understanding but are prone to adversarial attacks. Existing defenses often demand costly retraining or significant architecture changes. We introduce a lightweight defense using tensor…

Representation disentanglement aims at learning interpretable features, so that the output can be recovered or manipulated accordingly. While existing works like infoGAN and AC-GAN exist, they choose to derive disjoint attribute code for…

Deep learning based generative adversarial networks (GAN) can effectively perform image reconstruction with under-sampled MR data. In general, a large number of training samples are required to improve the reconstruction performance of a…

Image reconstruction is an essential step of every medical imaging method, including Photoacoustic Tomography (PAT), which is a promising modality of imaging, that unites the benefits of both ultrasound and optical imaging methods.…

As adversarial attacks against machine learning models have raised increasing concerns, many denoising-based defense approaches have been proposed. In this paper, we summarize and analyze the defense strategies in the form of symmetric…

Current vision systems typically assign fixed-length representations to images, regardless of the information content. This contrasts with human intelligence - and even large language models - which allocate varying representational…

Generative Adversarial Networks (GANs) have been widely-used in image translation, but their high computation and storage costs impede the deployment on mobile devices. Prevalent methods for CNN compression cannot be directly applied to…

Computed medical imaging systems require a computational reconstruction procedure for image formation. In order to recover a useful estimate of the object to-be-imaged when the recorded measurements are incomplete, prior knowledge about the…

Dense image alignment from RGB-D images remains a critical issue for real-world applications, especially under challenging lighting conditions and in a wide baseline setting. In this paper, we propose a new framework to learn a pixel-wise…

We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvement has been achieved, the quality of synthesized images is far from satisfactory due to three largely unresolved challenges. 1) The…

It has been well demonstrated that adversarial examples, i.e., natural images with visually imperceptible perturbations added, generally exist for deep networks to fail on image classification. In this paper, we extend adversarial examples…

Recently, a multitude of methods for image-to-image translation have demonstrated impressive results on problems such as multi-domain or multi-attribute transfer. The vast majority of such works leverages the strengths of adversarial…

Existing methods of 3D dense face alignment mainly concentrate on accuracy, thus limiting the scope of their practical applications. In this paper, we propose a novel regression framework named 3DDFA-V2 which makes a balance among speed,…

Generative Adversarial Networks (GANs) are considered the state-of-the-art in the field of image generation. They learn the joint distribution of the training data and attempt to generate new data samples in high dimensional space following…

The problem of generating textual descriptions for the visual data has gained research attention in the recent years. In contrast to that the problem of generating visual data from textual descriptions is still very challenging, because it…