NYU Depth V2

The NYU Depth V-2 dataset is a benchmark that contains RGB images paired with corresponding depth maps, used to evaluate monocular depth estimation models.

Papers using NYU Depth V2 (2)

SPACE-CLIP: Spatial Perception via Adaptive CLIP Embeddings for Monocular Depth Estimation2026Geometry-Aware Sparse Depth Sampling for High-Fidelity RGB-D Depth Completion in Robotic Systems2025