Los probadores del futuro en los medios de comunicación

Los probadores del futuro, el último trabajo del Dr. Sergio Escalera, líder del grupo de investigación Human Pose Recovery and Behavior Analysis del Centro de Visión por Computador (CVC) – Universidad de Barcelona (UB), sigue de actualidad. En las últimas semanas ha suscitado el interés de medios de comunicación tales cómo la Agencia SINC, Onda … Read more

El Centre de Visió per Computador s’uneix a la carta oberta de l’ACER “Ara més que mai: cal impulsar la ciència i la innovació”

El Dr. Josep Llados, Director del Centre de Visió per Computador (CVC) i membre de la junta de l’Associació Catalana d’Entitats de Recerca (ACER), ha signat la carta oberta “Ara més que mai: cal impulsar la ciència i la innovació” on l’ACER demana al futur nou govern català aprofitar els fons de recuperació de la … Read more

The fitting rooms of the future

Researchers from the Computer Vision Center (CVC) and the University of Barcelona (UB) have developed, using deep learning, CLOTH3D, the first 3D big scale synthetic dataset for simulating clothes on top of different body shapes. This dataset is the first step to allow virtual enhanced try-ons experience.

Every day, more and more people buy their clothes using virtual platforms, and the current pandemic situation is even speeding up this trend. The advantages of this new way of shopping are evident, but it has some shortcomings too. One of the most important is that people cannot try on the clothes before receiving it at their place. To solve this problem, Artificial Intelligence and deep learning are playing a key role, since they are allowing modelling, recovery and generation of 3D model clothes. These models will mean a breakthrough for enhanced virtual try-ons experience, reducing designer’s and animator’s workload.

Nowadays, it exits models for simulating clothes on top of body shapes, but they are almost focused on 2D. This is because 3D models need an enormous amount of data, and available 3D cloth data are very scarce. There are three main strategies in order to produce data of 3D-dressed humans: 3D scans, 3D from conventional images, and synthetic generation. In the case of 3D scans, they are costly, and at most, they can produce a single mesh (human + garments). Alternatively, datasets that infer 3D geometry of clothes from conventional images are inaccurate and cannot properly model cloth dynamics. Finally, synthetic data is easy to generate and is ground truth error-free.

Researchers from the Human Pose Recovery and Behavior Analysis Group at the Computer Vision Center (CVC) – University of Barcelona (UB) chose this last path and developed CLOTH3D, the first big-scale synthetic dataset of 3D clothed human sequences, which was recently published in the Computer Vision – ECCV 2020 journal.  “As a lot of data is needed for developing 3D models, we decided to generate our own data. We have designed and released the biggest dataset of this kind with a strong outfit variability and rich cloth dynamics”, explained Hugo Bertiche (UB – CVC).

CLOTH3D contains a large variability on garment type, topology, shape, size, tightness and fabric. Clothes are simulated on top of thousands of different pose sequences and body shapes, generating realistic cloth dynamics. CLOTH3D is unique in terms of garment, shape, and pose variability, including more than 2 million 3D samples. “We developed a generation pipeline that creates a unique outfit for each sequence in terms of garment type, topology, shape, size, tightness and fabric. While other datasets contain just a few different garments, ours is the biggest data set in this field nowadays, with thousands of different garments. But we did not focus only on its development, we also published it in open access, so it is available for all types of audiences”, Dr. Sergio Escalera (CVC-UB) pointed out.

But cloth manufacturing industry is not the only one that could take advantage of this dataset, “the entertainment industry could also benefit, since computer-generated image movies and videogames could be even more realistic”, argue Dr. Meysam Madadi (CVC). But there is still plenty of work to do, “understanding 3D garments through deep learning is still in early stages. On one hand, while our dataset covers most day-to-day garment variability, outfit styles are only limited by imagination. Faster, automatic and smart garment design could lead to many very interesting applications. On the other hand, cloth dynamics are extremely complex and challenging, and they have been barely tackled in very naive ways. Further exploring is a must for this community. Finally, real fabrics are much more than what simulators usually provide, deep learning has yet to find the proper way to model extremely fine and chaotic details such as wrinkles and also objects of arbitrary geometry related to outfits, such as hats, glasses, gloves, shoes, trinkets and more”, concluded H. Bertiche.

Reference:

Bertiche H., Madadi M., Escalera S. (2020) CLOTH3D: Clothed 3D Humans. Computer Vision – ECCV 2020. Lecture Notes in Computer Science, vol 12540. Springer, Cham. DOI: 10.1007/978-3-030-58565-5_21

New advances in the detection of bias in face recognition algorithms

A team from the Computer Vision Center (CVC) and the University of Barcelona has published the results of a study that evaluates the accuracy and bias in gender and skin colour of automatic face recognition algorithms tested with real world data. Although the top solutions exceed the 99.9% of accuracy, researchers have detected some groups … Read more

The role of the CVC in the fight against Covid-19 and lung cancer

La Vanguardia -in its printed edition- and Univadis Spain, featured the CVC research aimed to develop a digital biopsia that may be used in the diagnosis of Covid-19 and lung cancer. Members of the Interactive Augmented Modelling for Biomedicine (IAM4B) leaded by Dr. Dèbora Gil and Dr. Carles Sánchez, in collaboration with researchers from the … Read more

Time Machine project at Equal Times

The Time Machine project has been mentioned in this article about Big Data and collective memory featured at the digital magazine Equal Times (in English, Spanish and French): https://www.equaltimes.org/history-according-to-google-why#.XZMnjGZS-Uk  

Dr. Antonio López’s article at El Periodico

Dr. Antonio Lopez gives his view about the future of mobility and autonomous driving with an opinion piece at El Periodico (in Spanish). Read the full article here: El Periódico (15/08/2019): El vehículo autónomo, un reto a corto plazo   Related articles:  The Future Of Autonomous Cars: Understanding The City With The Use Of Videogames … Read more

Dr. Josep Lladós at El Suplement de Catalunya Radio

This Summer, our Director, Dr. Josep Lladós, was interviewed at El Suplement de Catalunya Radio in which he talked about the future of mobility.  The podcast can be found here (in Catalan):  https://www.ccma.cat/catradio/alacarta/el-suplement/val-la-pena-comprar-un-vehicle-electric-com-ens-mourem-en-un-futur-els-cotxes-conduiran-sols/audio/1047407/#.XVgb7LCDRzQ.twitter

CVC at Mobile World Congress 2019

The Computer Vision Center presented some of its latest technology at this year’s edition of the Mobile World Congress at the Catalan Pavilion (CS20).

Mobile World Congress (MWC) is the most important mobile event in the world that promotes the sector of the information and communication technologies. This year, this relevant event took place from the 25th to the 28th of February and 109.000 visitors and more than 2.400 companies all over the world attended to Fira de Barcelona in order to show and discover the latest innovations and leading-edge technology.

The Computer Vision Center was one of the 46 Catalan companies and institutions that presented their solutions in a stand within the Catalan Government pavilion, located in the central part of the Congress (Congress Square 20). The CVC had the opportunity to widen horizons presenting its research to a high number of professionals from different businesses worldwide and gaining reputation at a local scale with the visit of different personalities, journalists and politicians, such as the Right Honourable President of the Government of Catalonia, Quim Torra.

CVC presented its research focusing on three demonstrations: a software that predicts people’s personality traits in first-impressions, different tools for image retrieval using text or sketches and BronchoX, a service for lung cancer biopsy. Moreover, the last day of the congress, CVC team presented a demonstration on Autonomous Driving in the front part of the Catalan pavilion in which attendants had to race against the Artificial Intelligence inside our Carla Simulator.

Four days of intense work and networking in which hundreds of visitors came to our stand to discover the technologies and all aspects of CVC’s work.

In the media:

El Punt Avui, 27/02/2019, Innovació multidisciplinària

Vila Web, 25/02/2019: Un centenar d’empreses catalanes es fan un lloc al MWC amb solucions en mobilitat, logística i ciutats intel·ligents

Segre, 27/02/2019, Tecnologia lleidatana a la segona jornada de l’MWC

Regió 7, 25/02/2019: Un centenar d’empreses catalanes es fan un lloc al MWC

Aldia.cat, 25/02/2019: Un centenar d’empreses catalanes es fan un lloc al MWC amb solucions en mobilitat, logística i ciutats intel·ligents

 

 

Have a look at our Mobile World Congress 2019 Moment in Twitter: https://twitter.com/i/moments/1093800699673092097?s=13

Dr. Antonio López and Meritxell Bassolas at Vallès Visió

Dr. Antonio López and Meritxell Bassolas, CVC Knowledge and Technology Manager, were interviewed at Àmbit B30 (Vallès Visió) to talk about Autonomous Driving. In the program, CVC technologies on this field such as Elektra, Synthia and Carla are explained. You can watch the video here (in Catalan): http://www.vallesvisio.cat/ambit-b30-15-10-2018/