Planar Photometric Scene Reconstruction

This project aims to develop a new method for creating realistic 3D digital models from photographs, specifically improving how flat and texture-less surfaces are reconstructed—an area where current techniques often fail. By combining two approaches—2D representations for flat areas and 3D representations for more complex shapes—the method improves both the visual appearance and accuracy of the final model. The system is built as a feed-forward model that automatically detects and refines planar regions, enabling fast and consistent reconstruction across diverse indoor scenes.

Faculty Supervisor:

Andrea Tagliasacchi

Student:

Partner:

University College London

Discipline:

Computer science

Sector:

Education

University:

Simon Fraser University

Program:

Globalink Research Award

Related projects

Discover more projects across a range of sectors and discipline — from AI to cleantech to social innovation.

View all
Current openings

Find the perfect opportunity to put your academic skills and knowledge into practice!

Find Projects

Mitacs Partners

The strong support from governments across Canada, international partners, universities, colleges, companies, and community organizations has enabled Mitacs to focus on the core idea that talent and partnerships power innovation — and innovation creates a better future.

Government
Academic
Industry
Innovation
International

International

Load More

International

Load More

Join a thriving innovation ecosystem.

Subscribe to our newsletter now!

Subscribe

Mitacs — Return on Innovation

Mitacs is funded by the Government of Canada, the Government of Alberta, the Government of British Columbia, Research Manitoba, the Government of New Brunswick, the Government of Newfoundland and Labrador, the Government of Nova Scotia, the Government of Ontario, Innovation PEI, the Government of Quebec, the Government of Saskatchewan, and the Government of Yukon.