Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

Université de Montréal

$42,000.00

Modelling and animation via intuitive input

EF 2024-25

Résumé
Modern manufacturing, industrial design, and entertainment industries rely on content creation, such as creating 2D/3D digital shapes and animating them. Artists and engineers model characters and complex industrial parts for games, movies, and subsequent fabrication, easily spending from hours to weeks on a single model. Unfortunately, a significant amount of this time is wasted on non-creative work due to shape modelling and animation tools that can be, especially for newcomers, unintuitive and hard to use. The main problem with the modern modelling and animation software is that it does not align with the creative process of artists: While creative process needs freedom of exploration and focus on the main idea of a shape or animation, modern software typically forces artists to focus on technical details and tools with ever increasing complexity. For professionals, these technical details are a time-consuming distraction from the creative process, raising production costs and limiting creativity; for hobbyists, such complex tools often create entry barriers into this discipline. Despite such difficulty explaining shapes and animations to a computer, humans seem to have no problem imagining shapes and animations, explaining them to other people, or capturing their complex ideas with a pen and paper using just a few sketch strokes. My long-term vision is to improve 2D/3D software to make modelling and animation as easy and expressive, harnessing the artistic creativity, while maintaining high standards of quality of results. With my research group, we will create modelling and animation systems focused on more natural interactions that harness the creative freedom instead of limiting it. For instance, our software will be able to understand natural sketches directly, whether created with traditional pen and paper or tablets; our software may use natural language to clarify the 3D model the artist would like, or even allow artists to create surfaces with a literal wave of a hand or with a few strokes drawn in 3D with modern virtual reality (VR) headsets. The main challenge though is that while hand gestures, sketches, and natural language are easy to understand for humans, they are notoriously challenging to interpret for a computer. The difficulty comes from the fact that these forms of input are ambiguous and somewhat open to interpretation - a task that computers usually struggle with. To address this challenge, my work will explore the fundamental issues underlying the algorithmic understanding of these inputs, and immediately apply these findings to practical applied problems. Combining techniques from various areas of mathematics, recent developments in machine learning, insights from perception research as well as artistic literature, we will come significantly closer to my long-term vision.
Programme
Discovery Grants Program - Individual
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2024-04968
Name nom
Bessmeltsev, Mikhail
Department département
DIRO
Organization id
63
Institution établissement
Université de Montréal
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
42000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2707
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Graphics
Research subject fr
Infographie
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Modelling and animation via intuitive input
Keywords
geometry processing; geometric modelling; sketch processing; virtual reality; differential operators; inbetweening; vector graphics; sketching
Application summary
Modern manufacturing, industrial design, and entertainment industries rely on content creation, such as creating 2D/3D digital shapes and animating them. Artists and engineers model characters and complex industrial parts for games, movies, and subsequent fabrication, easily spending from hours to weeks on a single model. Unfortunately, a significant amount of this time is wasted on non-creative work due to shape modelling and animation tools that can be, especially for newcomers, unintuitive and hard to use. The main problem with the modern modelling and animation software is that it does not align with the creative process of artists: While creative process needs freedom of exploration and focus on the main idea of a shape or animation, modern software typically forces artists to focus on technical details and tools with ever increasing complexity. For professionals, these technical details are a time-consuming distraction from the creative process, raising production costs and limiting creativity; for hobbyists, such complex tools often create entry barriers into this discipline. Despite such difficulty explaining shapes and animations to a computer, humans seem to have no problem imagining shapes and animations, explaining them to other people, or capturing their complex ideas with a pen and paper using just a few sketch strokes. My long-term vision is to improve 2D/3D software to make modelling and animation as easy and expressive, harnessing the artistic creativity, while maintaining high standards of quality of results. With my research group, we will create modelling and animation systems focused on more natural interactions that harness the creative freedom instead of limiting it. For instance, our software will be able to understand natural sketches directly, whether created with traditional pen and paper or tablets; our software may use natural language to clarify the 3D model the artist would like, or even allow artists to create surfaces with a literal wave of a hand or with a few strokes drawn in 3D with modern virtual reality (VR) headsets. The main challenge though is that while hand gestures, sketches, and natural language are easy to understand for humans, they are notoriously challenging to interpret for a computer. The difficulty comes from the fact that these forms of input are ambiguous and somewhat open to interpretation - a task that computers usually struggle with. To address this challenge, my work will explore the fundamental issues underlying the algorithmic understanding of these inputs, and immediately apply these findings to practical applied problems. Combining techniques from various areas of mathematics, recent developments in machine learning, insights from perception research as well as artistic literature, we will come significantly closer to my long-term vision.