Project Details
Description
3D Reconstruction is a key enabling technology for many applications such as city modeling, robot navigation and mapping, and smart video surveillance. Existing methods rely heavily on motion-estimation, thus places serious restrictions to their application scope, making them fundamentally not suitable for processing modern distributed image databases containing unordered images. This project aims to develop new theory and methodology that are capable of efficiently reconstructing 3D from massive unordered images. The outcomes will not only advance the frontier of computer vision research, but also significantly boost the social and economical impacts of 3D reconstruction technology.
Status | Finished |
---|---|
Effective start/end date | 1/07/12 → 30/06/16 |
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.