mDERS: 0.3134
Papers with Code · CC BY-SA 4.0
Depth Estimation
Depth Estimation is the task of measuring the distance of each pixel relative to the camera. Depth is extracted from either monocular (single) or stereo (multiple views of a scene) images. Traditional methods use multi-view geometry to find the relationship between the images. Newer methods can directly estimate depth by minimizing the regression loss, or by learning to generate a novel view from a sequence. The most popular benchmarks are KITTI and NYUv2. Models are typically evaluated according to a RMS metric.
<span class="description-source">Source: DIODE: A Dense Indoor and Outdoor DEpth Dataset </span>
논문
Abs Rel: 0.717SQ Rel: 37.164RMSE: 74.552RMSE log: 0.882
RMSE: 0.232
absolute relative error: 0.121RMSE: 6.097Delta < 1.25: 0.871
Abs Rel: 0.071
Abs Rel: 0.134RMSE log: 0.188
absolute relative error: 0.088Sq Rel: 0.979RMSE: 4.60RMSE log: 0.154
RMSE: 0.397absolute relative error: 0.128log 10: 0.056Delta < 1.25: 0.825
RMSE: 0.335absolute relative error: 0.114log 10: 0.034Delta < 1.25: 0.937
Abs Rel: 0.4040SQ Rel: 6.3902RMSE: 13.685RMSE log: 0.4383
Abs Rel: 0.424Sq Rel: 3.075RMSE: 6.757
absolute relative error: 0.145Sq Rel: 2.119RMSE: 10.596RMSE log: 0.237
RMSE: 6.78
Abs Rel: 0.1425SQ Rel: 3.6798RMSE: 8.8641RMSE log: 0.24571
Absolute relative error (AbsRel): 0.097RMSE: 5.827 RMSE log: 0.154Square relative error (SqRel): 0.792
Abs Rel: 0.2410SQ Rel: 5.5321RMSE: 12.599RMSE log: 0.3618
Root mean square error (RMSE): 0.427Log root mean square error (RMSE_log): 0.248Mean average error (MAE) : 0.291Absolute relative error (AbsRel): 0.197
Abs Rel: 0.377Sq Rel: 4.9RMSE: 8.388
Abs Rel: 0.299Sq Rel: 1.931RMSE: 6.672
Absolute relative error (AbsRel): 0.089RMSE: 5.481RMSE log: 0.139Square relative error (SqRel): 1.051
Root mean square error (RMSE): 0.374Log root mean square error (RMSE_log): 0.213Mean average error (MAE) : 0.253Absolute relative error (AbsRel): 0.175
absolute relative error: 0.151Sq Rel: 3.591RMSE: 14.350RMSE log: 0.172
Abs Rel: 0.3136SQ Rel: 8.7127RMSE: 13.595RMSE log: 0.4380