Results for HSM-Net_RVC
Submission data
Full name | Hierarchical Deep Stereo Matching on High- Resolution Images |
Description | An end-to-end framework that searches for
correspondences incrementally over a coarse-to-fine hierarchy designed for high-resolution stereo matching. |
Parameters | - Middlebury model ran at 3.2X original ETH3D resolution;
- max_disparity set to 320px (before upsampling) |
Publication title | Hierarchical Deep Stereo Matching on High-resolution Images |
Publication authors | Gengshan Yang, Joshua Manela, Michael Happold, and Deva Ramanan |
Publication venue | CVPR 2019 |
Publication URL | https://github.com/gengshan-y/high-res-stereo |
Programming language(s) | Python |
Hardware | TitanXp |
Website | https://github.com/gengshan-y/high-res-stereo |
Source code or download URL | https://github.com/gengshan-y/high-res-stereo |
Submission creation date | 12 Aug, 2020 |
Last edited | 14 Aug, 2020 |
High-res multi-view results
Info | all | high-res multi-view | indoor | outdoor | botani. | boulde. | bridge | door | exhibi. | lectur. | living. | lounge | observ. | old co. | statue | terrac. |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
No results yet. |
Low-res many-view results
Info | all | low-res many-view | indoor | outdoor | delivery area | electro | forest | playground | terrains |
---|---|---|---|---|---|---|---|---|---|
No results yet. |