5,337
edits
360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume: Difference between revisions
360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume (view source)
Revision as of 00:39, 16 June 2020
, 16 June 2020→3D Encoder-Decoder
No edit summary |
|||
| Line 84: | Line 84: | ||
They learn the optimal step sizes by applying a 7x1 Conv2D CNN. | They learn the optimal step sizes by applying a 7x1 Conv2D CNN. | ||
==3D Encoder-Decoder== | ===3D Encoder-Decoder=== | ||
Next they pass the cost volume into a 3 3D hourglass encoder-decoder CNNs which regress the stereo disparity. | Next they pass the cost volume into a 3 3D hourglass encoder-decoder CNNs which regress the stereo disparity. | ||