Pose-driven attention-guided image generation for person re-Identification

Khatun, Amena; Denman, Simon; Sridharan, Sridha; Fookes, Clinton

doi:10.1016/j.patcog.2022.109246

Cited by 34 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BiGraphGAN (Tang et al 2023) captures the crossing long-range relations between source and target pose through bipartite to mitigate the challenges caused by pose deformation. Khatun et al (Khatun et al 2023) put forward a network structure to transfer subject pose through attention. Here, both an appearance discriminator and a pose discriminator are used to guide the synthesizing training.…”

Section: Related Workmentioning

confidence: 99%

“…The Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24) (Tang et al 2023;Khatun et al 2023;Men et al 2020;Roy et al 2023;Zhu et al 2019;Tang et al 2020;Zhang et al 2022Zhang et al , 2021Lv et al 2021;Zhang, Liu, and Li 2020;Zhou et al 2022;Li, Zhang, and Wang 2021;Bhunia et al 2023), and hence the overall synthesizing course could be tightly controlled through building The pose skeletons P s and P t are first extracted from corresponding input images, which is conducted mainly based on OpenPose (Cao et al 2017). Then we construct a three layers fully connected network as Pose Encoder to acquire their 512 dimensions features f Ps and f Pt .…”

Section: Global Evolution Constraintsmentioning

confidence: 99%

“…Competitive process originated Generative Adversarial Networks (GANs) (Gui et al 2023) is a powerful modeling architecture famous for prominent missing information compensation and complex content generation capability. Thus, this structure is an evident characteristic of numerous pose generation approaches (Tang et al 2023;Khatun et al 2023;Men et al 2020;Roy et al 2023;Zhu et al 2019;Tang et al 2020;Zhang et al 2022Zhang et al , 2021. Knowledge transferring in feature space is also a popular way to realize pose transformation (Khatun et al 2023;Lv et al 2021;Zhang, Liu, and Li 2020), where multistage information fusing is widely used to release the stress of missing information modeling.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, this structure is an evident characteristic of numerous pose generation approaches (Tang et al 2023;Khatun et al 2023;Men et al 2020;Roy et al 2023;Zhu et al 2019;Tang et al 2020;Zhang et al 2022Zhang et al , 2021. Knowledge transferring in feature space is also a popular way to realize pose transformation (Khatun et al 2023;Lv et al 2021;Zhang, Liu, and Li 2020), where multistage information fusing is widely used to release the stress of missing information modeling. In additional, newly developed attention centered Transformer structure has also proved its effectiveness for robust modeling human pose variation (Zhou et al 2022;Zhang et al 2022).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Direct May Not Be the Best: An Incremental Evolution View of Pose Generation

Li,

Xiao,

Geng

et al. 2024

AAAI

View full text Add to dashboard Cite

Pose diversity is an inherent representative characteristic of 2D images. Due to the 3D to 2D projection mechanism, there is evident content discrepancy among distinct pose images. This is the main obstacle bothering pose transformation related researches. To deal with this challenge, we propose a fine-grained incremental evolution centered pose generation framework, rather than traditional direct one-to-one in a rush. Since proposed approach actually bypasses the theoretical difficulty of directly modeling dramatic non-linear variation, the incurred content distortion and blurring could be effectively constrained, at the same time the various individual pose details, especially clothes texture, could be precisely maintained. In order to systematically guide the evolution course, both global and incremental evolution constraints are elaborately designed and merged into the overall framework. And a novel triple-path knowledge fusion structure is worked out to take full advantage of all available valuable knowledge to conduct high-quality pose synthesis. In addition, our framework could generate a series of valuable by-products, namely the various intermediate poses. Extensive experiments have been conducted to verify the effectiveness of the proposed approach. Code is available at https://github.com/Xiaofei-CN/Incremental-Evolution-Pose-Generation.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Global Evolution Constraintsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Direct May Not Be the Best: An Incremental Evolution View of Pose Generation

Li,

Xiao,

Geng

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…To analyze the state-of-the-art in what concerns GANs used for synthetic data generation, as well as synthetic data generation methods, we reviewed recently published scientific papers [ 21 , 22 , 23 ]. Pose-driven attention-guided image generation for person re-Identification proposed in [ 24 ] by Amena et al introduces attentive learning and transferring the subject pose through an attention mechanism based on GAN. In [ 25 ], the study aimed to synthesize artificial lung images from corresponding positional and semantic annotations using two generative adversarial networks and databases of real computed tomography scans.…”

Section: Related Workmentioning

confidence: 99%

Evaluating Synthetic Medical Images Using Artificial Intelligence with the GAN Algorithm

Abdusalomov

Nasimov

Nasimova

et al. 2023

Sensors

View full text Add to dashboard Cite

In recent years, considerable work has been conducted on the development of synthetic medical images, but there are no satisfactory methods for evaluating their medical suitability. Existing methods mainly evaluate the quality of noise in the images, and the similarity of the images to the real images used to generate them. For this purpose, they use feature maps of images extracted in different ways or distribution of images set. Then, the proximity of synthetic images to the real set is evaluated using different distance metrics. However, it is not possible to determine whether only one synthetic image was generated repeatedly, or whether the synthetic set exactly repeats the training set. In addition, most evolution metrics take a lot of time to calculate. Taking these issues into account, we have proposed a method that can quantitatively and qualitatively evaluate synthetic images. This method is a combination of two methods, namely, FMD and CNN-based evaluation methods. The estimation methods were compared with the FID method, and it was found that the FMD method has a great advantage in terms of speed, while the CNN method has the ability to estimate more accurately. To evaluate the reliability of the methods, a dataset of different real images was checked.

show abstract

Frontal person image generation based on arbitrary‐view human images

Zhang,

Chen

et al. 2024

Computer Animation & Virtual

View full text Add to dashboard Cite

Frontal person images contain the richest detailed features of humans, which can effectively assist in behavioral recognition, virtual dress fitting and other applications. While many remarkable networks are devoted to the person image generation task, most of them need accurate target poses as the network inputs. However, the target pose annotation is difficult and time‐consuming. In this work, we proposed a first frontal person image generation network based on the proposed anchor pose set and the generative adversarial network. Specifically, our method first classify a rough frontal pose to the input human image based on the proposed anchor pose set, and regress all key points of the rough frontal pose to estimate an accurate frontal pose. Then, we consider the estimated frontal pose as the target pose, and construct a two‐stream generator based on the generative adversarial network to update the person's shape and appearance feature in a crossing way and generate a realistic frontal person image. Experiments on the challenging CMU Panoptic dataset show that our method can generate realistic frontal images from arbitrary‐view human images.

show abstract

Pose-driven attention-guided image generation for person re-Identification

Cited by 34 publications

References 10 publications

Direct May Not Be the Best: An Incremental Evolution View of Pose Generation

Direct May Not Be the Best: An Incremental Evolution View of Pose Generation

Evaluating Synthetic Medical Images Using Artificial Intelligence with the GAN Algorithm

Frontal person image generation based on arbitrary‐view human images

Contact Info

Product

Resources

About