Table 6 Performance comparison of different convolutional attention modules.

From: A simple monocular depth estimation network for balancing complexity and accuracy

Method

\(\delta _1\uparrow\)

AbsRel\(\downarrow\)

RMSE\(\downarrow\)

Params\(\downarrow\)

Encoder(MSCAN)39+Decoder(Ours)+WAT+SENet67

0.919

0.093

0.336

30.6M

Encoder(MSCAN)39+Decoder(Ours)+WAT+CABM68

0.921

0.093

0.335

30.6M

Encoder(MSCAN)39+Decoder(Ours)+WAT+SCConv69

0.918

0.094

0.337

30.7M

Encoder(MSCAN)39+Decoder(Ours)+WAT+LMC

0.925

0.091

0.331

30.9M

  1. The best result is indicated in bold.
Back to article page