RMSE: 0.206absolute relative error: 0.056Delta < 1.25: 0.984Delta < 1.25^2: 0.998
Papers with Code · CC BY-SA 4.0
Monocular Depth Estimation
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>
개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.
벤치마크
Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.
Dataset기록된 모델 예시MetricPaperCode
IndoorDepth
Root mean square error (RMSE): 0.494Absolute relative error (AbsRel): 0.126delta_1: 84.5delta_2: 96.5
논문
코드
데이터셋
25개논문
absolute relative error: 0.050Delta < 1.25: 0.972
absolute relative error: 0.043Delta < 1.25: 0.981
absolute relative error: 0.052Delta < 1.25: 0.966
RMSE: 0.251absolute relative error: 0.051
RMSE: 0.128absolute relative error: 0.026Delta < 1.25: 0.988Delta < 1.25^2: 1.000
RMSE: 0.183absolute relative error: 0.047Delta < 1.25: 0.989Delta < 1.25^2: 0.998
absolute relative error: 0.046Delta < 1.25: 0.977
RMSE: 0.224absolute relative error: 0.055Delta < 1.25: 0.964Delta < 1.25^2: 0.991
RMSE: 0.201absolute relative error: 0.058Delta < 1.25: 0.984Delta < 1.25^2: 0.997
RMSE: 0.180absolute relative error: 0.046Delta < 1.25: 0.988Delta < 1.25^2: 0.998
RMSE: 0.173absolute relative error: 0.044Delta < 1.25: 0.989Delta < 1.25^2: 0.998
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.