Saeed Ghorbani

Saeed Ghorbani

Auto-generated profile, based on publicly available information

Saeed Ghorbani

Ubisoft LaForge

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 June 2021 in PLOS ONE
Verified
Journal Article
Open access
PDF file
SGSaeed Ghorbani
Saeed Ghorbani
KMKimia Mahdaviani
Kimia Mahdaviani
ATAnne Thaler
Anne Thaler
KKKonrad Kording
Konrad Kording
DCDouglas James Cook
Douglas James Cook
NTNikolaus F. Troje
Nikolaus F. Troje
Large high-quality datasets of human body shape and kinematics lay the foundation for modelling and simulation approaches in computer vision, computer graphics, and biomechanics. Creating datasets that combine naturalistic recordings with high-accuracy data about ground truth body shape and pose is challenging because different motion recording systems are either optimized for one or the other. We address this issue in our dataset by using different hardware systems to record partially overlapping information and synchronized data that lend themselves to transfer learning. This multimodal dataset contains 9 hours of optical motion capture data, 17 hours of video data from 4 different points of view recorded by stationary and hand-held cameras, and 6.6 hours of inertial measurement units data recorded from 60 female and 30 male actors performing a collection of 21 everyday actions and sports movements. The processed motion capture data is also available as realistic 3D human meshes. We anticipate use of this dataset for research on human pose estimation, action recognition, motion modelling, gait analysis, and body shape reconstruction.

19 February 2023 in Computer Graphics Forum
Verified
Journal Article
Open access
SGSaeed Ghorbani
Saeed Ghorbani
YFYlva Ferstl
Ylva Ferstl
DHDaniel Holden
Daniel Holden
NTNikolaus F. Troje
Nikolaus F. Troje
MCMarc‐André Carbonneau
Marc‐André Carbonneau
We present ZeroEGGS, a neural network framework for speech‐driven gesture generation with zero‐shot style control by example. This means style can be controlled via only a short example motion clip, even for motion styles unseen during training. Our model uses a Variational framework to learn a style embedding, making it easy to modify style through latent space manipulation or blending and scaling of style embeddings. The probabilistic nature of our framework further enables the generation of a variety of outputs given the input, addressing the stochastic nature of gesture motion. In a series of experiments, we first demonstrate the flexibility and generalizability of our model to new speakers and styles. In a user study, we then show that our model outperforms previous state‐of‐the‐art techniques in naturalness of motion, appropriateness for speech, and style portrayal. Finally, we release a high‐quality dataset of full‐body gesture motion including fingers, with speech, spanning across 19 different styles. Our code and data are publicly available at https://github.com/ubisoft/ubisoft‐laforge‐ZeroEGGS.

24 November 2020 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
SGS. Ghorbani
S. Ghorbani
CWC. Wloka
C. Wloka
AEAli Etemad
Ali Etemad
MBM. A. Brubaker
M. A. Brubaker
NTN. F. Troje
N. F. Troje

12 June 2019
Verified
Book Chapter
Closed access
PDF file
SGSaeed Ghorbani
Saeed Ghorbani
AEAli Etemad
Ali Etemad
NTNikolaus F. Troje
Nikolaus F. Troje

4 June 2021 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
VDVandad Davoodnia
Vandad Davoodnia
SGSaeed Ghorbani
Saeed Ghorbani
AEAli Etemad
Ali Etemad

7 November 2022
Verified
Conference Paper
Open access
SGSaeed Ghorbani
Saeed Ghorbani
YFYlva Ferstl
Ylva Ferstl
MCMarc-André Carbonneau
Marc-André Carbonneau
We present our entry to the GENEA Challenge of 2022 on data-driven co-speech gesture generation. Our system is a neural network that generates gesture animation from an input audio file. The motion style generated by the model is extracted from an exemplar motion clip. Style is embedded in a latent space using a variational framework. This architecture allows for generating in styles unseen during training. Moreover, the probabilistic nature of our variational framework furthermore enables the generation of a variety of outputs given the same input, addressing the stochastic nature of gesture motion. The GENEA challenge evaluation showed that our model produces full-body motion with highly competitive levels of human-likeness.