Geometry and learning in 3D correspondence problems
Duration: 53 mins 33 secs
Share this media item:
Embed this media item:
Embed this media item:
About this item
| Description: |
Bronstein, A
Thursday 14th December 2017 - 11:30 to 12:30 |
|---|
| Created: | 2017-12-15 15:40 |
|---|---|
| Collection: | Variational methods and effective algorithms for imaging and vision |
| Publisher: | Isaac Newton Institute |
| Copyright: | Bronstein, A |
| Language: | eng (English) |
| Distribution: |
World
(downloadable)
|
| Explicit content: | No |
| Aspect Ratio: | 16:9 |
| Screencast: | No |
| Bumper: | UCS Default |
| Trailer: | UCS Default |
| Abstract: | The need to compute correspondence between three-dimensional objects is a fundamental ingredient in numerous computer vision and graphics tasks. In this talk, I will show how several geometric notions related to the Laplacian spectrum provide a set of tools for efficiently calculating correspondence between deformable shapes. I will also show how this framework combined with recent ideas in deep learning promises to bring correspondence problems to new levels of accuracy. |
|---|---|
Available Formats
| Format | Quality | Bitrate | Size | |||
|---|---|---|---|---|---|---|
| MPEG-4 Video | 640x360 | 1.94 Mbits/sec | 779.85 MB | View | Download | |
| WebM | 640x360 | 455.93 kbits/sec | 178.88 MB | View | Download | |
| iPod Video | 480x270 | 522.28 kbits/sec | 204.85 MB | View | Download | |
| MP3 | 44100 Hz | 249.73 kbits/sec | 98.07 MB | Listen | Download | |
| Auto * | (Allows browser to choose a format it supports) | |||||