Results for FC-DCNN v2
Submission data
| Full name | fully-convolutional densely-connected neural network |
| Description | We propose a novel lightweight network for stereo estimation. The method uses densely connected layer structures to learn expressive features without the need of fully-connected layers or 3D convolutions. This leads to a network structure with only 0.37M parameters while still having competitive results. The post-processing consists of filtering, a consistency check and hole filling. This paper has been accepted to the ICPR 2020 conference in Milan.
Second version. Slight changes over the first version due to better hyperparameter search. For more details check out the github page. |
| Programming language(s) | python |
| Hardware | GeForce 2080 GTX |
| Submission creation date | 29 Aug, 2024 |
| Last edited | 29 Aug, 2024 |
High-res multi-view results
| Info | all | high-res multi-view | indoor | outdoor | courty. | delive. | electro | facade | kicker | meadow | office | pipes | playgr. | relief | relief. | terrace | terrai. |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No results yet. | |||||||||||||||||
Low-res many-view results
| Info | all | low-res many-view | indoor | outdoor | lakeside | sand box | storage room | storage room 2 | tunnel |
|---|---|---|---|---|---|---|---|---|---|
| No results yet. | |||||||||
