Laboratory
News
Research
Social Media
- Linkedin
- Instagram
- Twitter
- YouTube
Contact
Restrict Area

Things we have done

RGB-D Descriptor for non-rigid deformations

» Next
Previous »

Accurately matching points accross different images viewing the same object or scene is a crucial step in many Computer Vision tasks. Most local image descriptors can handle image transformations up to some extent, such as illumination and perspective changes. However, most of them are not designed to cope with non-rigid deformations. In this project, we focus on improving local image description techniques to correctly handle non-rigid deformations, while also improving their discriminative power.

More

Contact

UFMG
+55 (31) 3409-5856
verlab (at) dcc (dot) ufmg (dot) br

Stay Connected

Github
Youtube

Visitors in last month

VeRLab - Computer Vision and Robotics Lab
Contact