Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

The University of British Columbia

$71,000.00

Human-centered Geometry Processing

FY 2024-25

Summary
Shape is a core characteristic of natural and human-made objects, and is the first property one must capture when digitally describing them. Geometry processing (GP) research investigates the creation and manipulation of such digital shapes. My proposal addresses human-centered GP problems, where the desired solutions are intuitively clear to human users or observers, but where the analytical formulation that matches this intuition is unknown. The lack of such formulations makes these problems inherently hard. The need for a human-centered GP approach arises for instance when users want to create or edit geometric content (be it design a new car or alter the look of a dress) and seek for an intuitive way to communicate their desired outcome to the GP software, when they wish for a software to perform tasks which artists or designers are adept at (e.g. effectively draw a shape), or when they want to perform at scale tasks that are easy but tedious for humans to perform (e.g. annotate sharp features on a 3D shape). My long-term research goal is to address such GP problems by applying insights about how humans perceive and communicate shape to each other to algorithmic, user-driven shape processing. My earlier work pioneered the use of human-centered GP methods for tasks such as garment design and, sketch processing. Within the timeline of this proposal I will address three new research directions in this space. CaptureIntent: Humans can mentally visualize the outcomes of the design tasks they wish to perform (e.g. the shape of a new controller they want to model). To implement these ideas, however, they must communicate them to the GP software via some user-interface (UI). Despite recent progress, performing these design tasks using existing UIs can take multiple hours and requires specialized modeling expertise. I will enable users to communicate the detailed GP task they wish to performs via intuitive interfaces by developing novel approaches for capturing user intent. MimicHumans: I will develop processing algorithms that mimic human performance on a range of GP tasks that humans are more adept at than current algorithms, but that require significant time or skill to perform manually. UsableML: ML tools hold huge promise in simplifying and speeding up human-centered GP. I'll use these methods when best suited for the problems at hand. At the same time current ML methods suffer from severe usability and control issues that must be addressed to unleash their potential. They also require energy-intensive and time-consuming offline training. I'll develop usable ML-based methods for practical, real-world GP tasks, by making them easier to control and reducing their environmental footprint. Impact: Jointly, these advances will enable a broad range of users to create, manipulate, and process 2D and 3D shapes for their applications and domains of interest, enhancing productivity and transforming design and manufacturing processes and practice.
Program
Discovery Grants Program - Individual
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
RGPIN-2024-03981
Name nom
Sheffer, Alla
Department département
Computer Sceince
Organization id
2
Institution établissement
The University of British Columbia
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
71000
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
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2700
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Information technology
Research subject fr
Technologie de l'information
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
Human-centered Geometry Processing
Keywords
geometry processing; human-centered geometry processing; computer graphics; shape modeling; perception-aware shape analysis; perception-driven modeleing; sketch-based modeling; non-photorealistic rendering; computational design
Application summary
Shape is a core characteristic of natural and human-made objects, and is the first property one must capture when digitally describing them. Geometry processing (GP) research investigates the creation and manipulation of such digital shapes. My proposal addresses human-centered GP problems, where the desired solutions are intuitively clear to human users or observers, but where the analytical formulation that matches this intuition is unknown. The lack of such formulations makes these problems inherently hard. The need for a human-centered GP approach arises for instance when users want to create or edit geometric content (be it design a new car or alter the look of a dress) and seek for an intuitive way to communicate their desired outcome to the GP software, when they wish for a software to perform tasks which artists or designers are adept at (e.g. effectively draw a shape), or when they want to perform at scale tasks that are easy but tedious for humans to perform (e.g. annotate sharp features on a 3D shape). My long-term research goal is to address such GP problems by applying insights about how humans perceive and communicate shape to each other to algorithmic, user-driven shape processing. My earlier work pioneered the use of human-centered GP methods for tasks such as garment design and, sketch processing. Within the timeline of this proposal I will address three new research directions in this space. CaptureIntent: Humans can mentally visualize the outcomes of the design tasks they wish to perform (e.g. the shape of a new controller they want to model). To implement these ideas, however, they must communicate them to the GP software via some user-interface (UI). Despite recent progress, performing these design tasks using existing UIs can take multiple hours and requires specialized modeling expertise. I will enable users to communicate the detailed GP task they wish to performs via intuitive interfaces by developing novel approaches for capturing user intent. MimicHumans: I will develop processing algorithms that mimic human performance on a range of GP tasks that humans are more adept at than current algorithms, but that require significant time or skill to perform manually. UsableML: ML tools hold huge promise in simplifying and speeding up human-centered GP. I'll use these methods when best suited for the problems at hand. At the same time current ML methods suffer from severe usability and control issues that must be addressed to unleash their potential. They also require energy-intensive and time-consuming offline training. I'll develop usable ML-based methods for practical, real-world GP tasks, by making them easier to control and reducing their environmental footprint. Impact: Jointly, these advances will enable a broad range of users to create, manipulate, and process 2D and 3D shapes for their applications and domains of interest, enhancing productivity and transforming design and manufacturing processes and practice.