VAREN: Very Accurate and Realistic Equine Network. S Zuffi, Y Mellbin, C Li, M Hoeschle, H Kjellstrom, S Polikovsky, E Hernlund, and MJ Black.
A novel 3D articulated parametric shape model learned from 3D scans of many real horses.
An automatic, objective method to measure and visualize volumetric changes in patients with facial palsy during 3D video recordings. T Büchner , S Sickert , GF Volk , J Denzler , O Guntinas-Lichius.
This data-driven method mitigates the risk of human biases in therapeutic evaluations and effectively transitions from static 2D images to dynamic 4D assessments of facial palsy state.
The Power of Properties: Uncovering the Influential Factors in Emotion Classification. T Büchner, N Penzel, O Guntinas-Lichius, J Denzler.
36 patients (25-72 years, 8 male, 28 female) with unilateral chronic synkinetic facial palsy, which is presumed to be a significant factor affecting classification, were recorded three times using the 30Hz 3dMDface system.
Design2Cloth: 3D Cloth Generation from 2D Masks. J Zheng, RA Potamias, S Zafeiriou.
We make a step towards automatic realistic garment design and propose Design2Cloth, a high fidelity 3D generative model trained on a real world dataset. The scans of a total of 2010 distinct subjects spanning different ages, body types and ethnicities were captured using a 3dMDbody System.
Fully automated landmarking and facial segmentation on 3D photographs. B Berends, F Bielevelt, R Schreurs, et al.
A deep learning-based approach for automated landmark extraction from 3dMD facial photographs was developed and its precision was evaluated. The results showed high precision and consistency in landmark annotation, comparable to manual and semi-automatic annotation methods.
Ultra-dense Motion Capture: An exploratory full-automatic approach for dense tracking of breast motion in 4D. Q-l Liu, K-l Yick, Y Sun, J Yip.
To develop sports bras that effectively limiting breast movement while minimize stress on the breast tissues, it is crucial to gain a comprehensive understanding of the breast movement and deformation patterns.
Impact of autologous breast reconstruction on bra fit. YT Liu, NH Khan, MC Bordes, et al.
Preoperative baseline breast measurements, age, and BMI can impact bra designs for breast cancer survivors who undergo autologous reconstruction due to size, shape, and symmetry changes. Bra needs of people who undergo autologous reconstruction differ from those who undergo implant-based reconstruction.
Automated three-dimensional analysis of facial asymmetry in patients with syndromic coronal synostosis: A retrospective study. TM Choi, X Liu, T Abdel-Alim, ML van Veelen, IMJ Mathijssen, EB Wolvius, GV Roshchupkin.
101 patients from 2005 to 2022 were selected for inclusion according to the following criteria: diagnosis molecularly confirmed; were of Caucasian descent; had only premature fusion of left and/or right coronal suture(s); had undergone only one craniofacial surgery; were younger than 18 years; had undergone no orthodontic treatment; had no extraction of permanent teeth; and had not undergone maxillary osteotomy.
A quantitative method for the assessment of facial attractiveness based on transfer learning with fine-grained image classification. LJ Lo, CT Yang, WC Chiang, HH Lin.
3dMD facial images and deep transfer learning have been firstly combined for evaluating the facial attractiveness in patients undergoing Orthognathic surgery.
The Florence multi-resolution 3D facial expression dataset. C Ferrari, S Berretti, P Pala, A Del Bimbo.
3D real scans: We acquired 3D scans of 20 subjects (5 females and 15 males) with a 3dMD HR scanner. Subjects are mainly students and university personnel, 30 years old on average.