Depth Estimation

Monocular depth estimation uses neural networks trained on paired image-depth data to predict a depth map from a single photo. The model learns to interpret visual cues that humans use for depth perception — relative size, occlusion, texture gradient, atmospheric haze, and perspective convergence. The resulting depth map assigns a distance value to each pixel, enabling 3D-aware editing operations. Applications include generating synthetic bokeh (background blur that follows real depth falloff), creating parallax effects for social media, enabling AR object placement, and improving AI segmentation accuracy. Smartphone portrait modes use depth estimation to separate subjects from backgrounds for real-time blur effects.