SOTAVerified

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.

Source: Defocus Deblurring Using Dual-Pixel Data

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 711–720 of 876 papers

TitleStatusHype
Improved Noise and Attack Robustness for Semantic Segmentation by Using Multi-Task Training with Self-Supervised Depth Estimation—0
On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: a Survey—0
DepthNet Nano: A Highly Compact Self-Normalizing Neural Network for Monocular Depth Estimation—0
RealMonoDepth: Self-Supervised Monocular Depth Estimation for General Scenes—0
Monocular Depth Estimation with Self-supervised Instance Adaptation—0
Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving ApplicationsCode1
Self-Supervised Monocular Scene Flow EstimationCode1
Guiding Monocular Depth Estimation Using Depth-Attention VolumeCode1
Towards Better Generalization: Joint Depth-Pose Learning without PoseNetCode1
The Edge of Depth: Explicit Constraints between Segmentation and DepthCode1
Show:102550
← PrevPage 72 of 88Next →

No leaderboard results yet.