From 2D to 3D geodesic-based garment matching

Avots, Egils; Madadi, Meysam; Escalera, Sérgio; Gonzàlez, Jordi; Baró, Xavier; Pällin, Paul; Anbarjafari, Gholamreza

doi:10.1007/s11042-019-7739-5

Cited by 5 publications

(3 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The objects that are placed in an AR space need to look and feel as if they are actually present in that space, rather than appearing as a simple overlay. This is typically achieved with high-resolution models and textures, reflection probes sampled from the camera [81,82], lighting color and direction estimation [83,84], surface and people detection [85], surface occlusion [86], virtual shadows [87], and subtle post-processing effects [88]. All of these bring an AR object closer to looking like a real object.…”

Section: Assets Used In Ar Applicationsmentioning

confidence: 99%

Augmented Reality: Current and New Trends in Education

Kamińska,

Zwoliński,

Laska-Leśniewicz

et al. 2023

Electronics

Self Cite

View full text Add to dashboard Cite

The educational landscape is an environment prone to change due to the volatile and ever-changing nature of the digital society in which we all live. Although the world moves at different speeds and any generalization is bound to have some exceptions, there is evidence from research conducted in different places and contexts that educational methods are becoming increasingly digitized and driven by technological innovation. Among the technological trends fueled in many cases by the COVID-19 pandemic and the need to stay at home but online, augmented reality solutions received an additional boost as a valid and versatile educational technology worth exploring and eventually integrating into several teaching methods already in use. Although the technology still faces problems related to affordability, accessibility, and the technical skills required of users, some ongoing projects have already provided evidence that using augmented reality solutions as teaching and learning tools can improve teacher and student learning outcomes by increasing engagement and interactivity. The same issues arose when personal computers, tablets, and smartphones were first discussed as valuable tools for education and have now found their way into most classrooms. This paper reviews some of the key concepts related to augmented reality, as well as some current trends, benefits, and concerns related to its integration into educational contexts in areas such as life sciences, engineering, and health. The work conducted and presented in this paper provides an interesting insight into a technology that has given rise to global phenomena such as Pokémon Go, and continues to improve in terms of portability, usability, and overall user experience. Throughout the paper and in the conclusion section, we discuss the relevance of using the best features of augmented reality and how they can contribute to positive educational outcomes.

show abstract

Section: Assets Used In Ar Applicationsmentioning

confidence: 99%

Augmented Reality: Current and New Trends in Education

Kamińska,

Zwoliński,

Laska-Leśniewicz

et al. 2023

Electronics

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are several key concepts and terms that one needs to understand when applying machine learning and computer vision in the fashion industry [5,6,7].…”

Section: Introductionmentioning

confidence: 99%

Generative AI-based Style Recommendation Using Fashion ItemDetection and Classification

Kalinin,

Jafari,

Avots

et al. 2024

Preprint

View full text Add to dashboard Cite

This research work focuses on the creation of a cutting-edge style recommendation system that uses generative AI and deep learning approaches to analyse fashion photos. The system is intended to process input images, such as selfies or studio-quality photos, and output a text file with extensive feedback on the individual's style and suggestions for improvement. The system consists of two main components: the YOLOv8 convolutional neural network, which detects and crops clothing items, and the GPT-4.0 large language model, which generates informative style commentary and recommendations. YOLOv8 is briefly trained on a specific dataset to improve its performance in recognising 10 different types of clothes, while GPT-4.0, which is accessible via the OpenAI API, is charged with giving cohesive and short style suggestions. To evaluate the success of the suggested solution, real experimental trials were conducted at many events in Madrid and Tallinn. Three well-known AI models were used for comparison: OpenAI's GPT-4.0 Vision, Google's Gemini 1.5 Pro, and Anthropic's Claude 3 - Opus. Participants judged the quality of each model's fashion recommendations. The results showed that GPT-4.0 Vision and Gemini 1.5 Pro had comparable average ratings, indicating higher perceived quality than Claude 3 - Opus. This research work demonstrates how cutting-edge computer vision and natural language processing technology may transform personalised fashion advising services, improving accuracy and relevance of style recommendations.

show abstract

“…Point set registration is a fundamental task in many computer vision applications, such as object tracking (Gao & Tedrake, 2018), shape retrieval (Berger et al, 2017) and contour matching (Avots et al, 2019). As illustrated in Fig.…”

Section: Introductionmentioning

confidence: 99%

Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration

Wang¹,

Xue²,

Ling³

et al. 2022

Preprint

View full text Add to dashboard Cite

Given two point sets, the problem of registration is to recover a transformation that matches one set to the other. This task is challenging due to the presence of the large number of outliers, the unknown non-rigid deformations and the large sizes of point sets. To obtain strong robustness against outliers, we formulate the registration problem as a partial distribution matching (PDM) problem, where the goal is to partially match the distributions represented by point sets in a metric space. To handle large point sets, we propose a scalable PDM algorithm by utilizing the efficient partial Wasserstein-1 (PW) discrepancy. Specifically, we derive the Kantorovich-Rubinstein duality for the PW discrepancy, and show its gradient can be explicitly computed. Based on these results, we propose a partial Wasserstein adversarial network (PWAN), which is able to approximate the PW discrepancy by a neural network, and minimize it by gradient descent. In addition, it also incorporates an efficient coherence regularizer for non-rigid transformations to avoid unrealistic deformations. We evaluate PWAN on practical point set registration tasks, and show that the proposed PWAN is robust, scalable and performs more favorably than the state-of-the-art methods.

show abstract

From 2D to 3D geodesic-based garment matching

Cited by 5 publications

References 53 publications

Augmented Reality: Current and New Trends in Education

Augmented Reality: Current and New Trends in Education

Generative AI-based Style Recommendation Using Fashion ItemDetection and Classification

Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration

Contact Info

Product

Resources

About