Papers with Code · CC BY-SA 4.0

Monocular Depth Estimation

Depth Estimation › Monocular Depth Estimation 283 평가 기록 25 datasets

Monocular Depth Estimation is the task of estimating the depth value (distance relative to the camera) of each pixel given a single (monocular) RGB image. This challenging task is a key prerequisite for determining scene understanding for applications such as 3D scene reconstruction, autonomous driving, and AR. State-of-the-art methods usually fall into one of two categories: designing a complex network that is powerful enough to directly regress the depth map, or splitting the input into bins or windows to reduce computational complexity. The most popular benchmarks are the KITTI and NYUv2 datasets. Models are typically evaluated using RMSE or absolute relative error.

<span class="description-source">Source: Defocus Deblurring Using Dual-Pixel Data </span>

논문

Self-Supervised Monocular Depth Hints

1909.09051 2019-09-19 이 페이지의 평가 1건
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

Toward Practical Monocular Indoor Depth Estimation

2112.02306 2021-12-04 이 페이지의 평가 1건
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