Depth Estimation
A computer vision task that predicts the distance of each pixel from the camera, creating a depth map from a single image or stereo pair.
Approaches
Monocular: Estimate depth from a single image using learned cues (relative size, occlusion, perspective). Stereo: Use two camera views to compute depth via disparity. LiDAR fusion: Combine camera and LiDAR data.
Applications
Autonomous driving, AR/VR, 3D reconstruction, robotics navigation, and computational photography (portrait mode blur).