Related papers: Exploring Dual-task Correlation for Pose Guided Pe…

Low-light image super-resolution (LLSR) is a challenging task due to the coupled degradation of low resolution and poor illumination. To address this, we propose the Guided Texture and Feature Modulation Network (GTFMN), a novel framework…

In recent years, 2D human pose estimation has made significant progress on public benchmarks. However, many of these approaches face challenges of less applicability in the industrial community due to the large number of parametric…

Personalized text-to-image generation methods can generate customized images based on the reference images, which have garnered wide research interest. Recent methods propose a finetuning-free approach with a decoupled cross-attention…

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…

Person re-identification (person Re-Id) aims to retrieve the pedestrian images of a same person that captured by disjoint and non-overlapping cameras. Lots of researchers recently focuse on this hot issue and propose deep learning based…

Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring poses of one person to others. Though many different methods have been proposed to generate images with high visual fidelity,…

The rapid advancement of Text-to-Image(T2I) generative models has enabled the synthesis of high-quality images guided by textual descriptions. Despite this significant progress, these models are often susceptible in generating contents that…

Recent works on pose-based gait recognition have demonstrated the potential of using such simple information to achieve results comparable to silhouette-based methods. However, the generalization ability of pose-based methods on different…

In this paper, we propose a novel cross-attention-based generative adversarial network (GAN) for the challenging person image generation task. Cross-attention is a novel and intuitive multi-modal fusion method in which an…

We investigate nearest neighbor and generative models for transferring pose between persons. We take in a video of one person performing a sequence of actions and attempt to generate a video of another person performing the same actions.…

In this paper we address the problem of generating person images conditioned on a given pose. Specifically, given an image of a person and a target pose, we synthesize a new image of that person in the novel pose. In order to deal with…

Text-to-image models (T2I) such as StableDiffusion have been used to generate high quality images of people. However, due to the random nature of the generation process, the person has a different appearance e.g. pose, face, and clothing,…

In the last two years, text-to-image diffusion models have become extremely popular. As their quality and usage increase, a major concern has been the need for better output control. In addition to prompt engineering, one effective method…

Unsupervised image translation aims to learn the transformation from a source domain to another target domain given unpaired training data. Several state-of-the-art works have yielded impressive results in the GANs-based unsupervised…

Action coordination in human structure is indispensable for the spatial constraints of 2D joints to recover 3D pose. Usually, action coordination is represented as a long-range dependence among body parts. However, there are two main…

Point cloud completion estimates complete shapes from incomplete point clouds to obtain higher-quality point cloud data. Most existing methods only consider global object features, ignoring spatial and semantic information of adjacent…

To synthesize high-quality person images with arbitrary poses is challenging. In this paper, we propose a novel Multi-scale Conditional Generative Adversarial Networks (MsCGAN), aiming to convert the input conditional person image to a…

Domain adaptation methods for 2D human pose estimation typically require continuous access to the source data during adaptation, which can be challenging due to privacy, memory, or computational constraints. To address this limitation, we…

Human densepose estimation, aiming at establishing dense correspondences between 2D pixels of human body and 3D human body template, is a key technique in enabling machines to have an understanding of people in images. It still poses…

Pose-guided person image synthesis aims to synthesize person images by transforming reference images into target poses. In this paper, we observe that the commonly used spatial transformation blocks have complementary advantages. We propose…