RMSE: 0.355absolute relative error: 0.098Delta < 1.25: 0.913Delta < 1.25^2: 0.987
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
RMSE: 0.364absolute relative error: 0.103Delta < 1.25: 0.903Delta < 1.25^2: 0.984
RMSE: 0.3046absolute relative error: 0.0864Delta < 1.25: 0.9361Delta < 1.25^2: 0.9916
RMSE: 0.322absolute relative error: 0.090Delta < 1.25: 0.929Delta < 1.25^2: 0.991
RMSE: 0.532absolute relative error: 0.138Delta < 1.25: 0.820Delta < 1.25^2: 0.956
RMSE: 0.330absolute relative error: 0.094Delta < 1.25: 0.925Delta < 1.25^2: 0.989
RMSE: 0.375absolute relative error: 0.104Delta < 1.25: 0.899Delta < 1.25^2: 0.985
RMSE: 0.354absolute relative error: 0.095Delta < 1.25: 0.919Delta < 1.25^2: 0.988
RMSE: 0.329absolute relative error: 0.094Delta < 1.25: 0.921Delta < 1.25^2: 0.990
RMSE: 0.345absolute relative error: 0.100Delta < 1.25: 0.913Delta < 1.25^2: 0.988
RMSE: 0.339absolute relative error: 0.096Delta < 1.25: 0.921Delta < 1.25^2: 0.989
RMSE: 0.279absolute relative error: 0.0907Delta < 1.25: 0.9497Delta < 1.25^2: 0.996
RMSE: 0.416absolute relative error: 0.111Delta < 1.25: 0.875Delta < 1.25^2: 0.976
RMSE: 0.398absolute relative error: 0.116Delta < 1.25: 0.875Delta < 1.25^2: 0.980
RMSE: 0.392Delta < 1.25^3: 0.995
RMSE: 0.344absolute relative error: 0.098Delta < 1.25: 0.915Delta < 1.25^2: 0.988
RMSE: 0.314absolute relative error: 0.087Delta < 1.25: 0.936Delta < 1.25^2: 0.992
RMSE: 0.321absolute relative error: 0.089Delta < 1.25: 0.932log 10: 0.039
RMSE: 0.352absolute relative error: 0.101Delta < 1.25: 0.910Delta < 1.25^2: 0.985
absolute relative error: 0.09Delta < 1.25: 0.916
RMSE: 0.351absolute relative error: 0.098Delta < 1.25: 0.91Delta < 1.25^2: 0.986
RMSE: 0.384absolute relative error: 0.105Delta < 1.25: 0.895Delta < 1.25^2: 0.983
RMSE: 0.311absolute relative error: 0.087Delta < 1.25: 0.936Delta < 1.25^2: 0.991
RMSE: 0.334absolute relative error: 0.095Delta < 1.25: 0.922Delta < 1.25^2: 0.992
RMSE: 0.331
RMSE: 0.429
RMSE: 0.356absolute relative error: 0.104Delta < 1.25: 0.898Delta < 1.25^2: 0.981
RMSE: 0.316absolute relative error: 0.088Delta < 1.25: 0.933Delta < 1.25^2: 0.992
RMSE: 0.357absolute relative error: 0.110Delta < 1.25: 0.904Delta < 1.25^2: 0.988