Understand this story
Apple Machine Learning Research has released the Depth Pro 2 model family for monocular metric depth estimation. Using a single scalable network, the model processes images, videos, and live camera feeds at native resolution and estimates depth in meters for each pixel; its design balances metric accuracy, sharp object boundaries, and temporal consistency across frames. Apple Machine Learning Research has also released the associated models, code, and weights. There are currently no other subsequent developments supported by factual evidence.
AI-generated from public reports
Latest development · Report
Apple Releases Depth Pro 2 Research on Monocular Metric Depth EstimationDevelopments
1 confirmed developments
Apple Machine Learning Research Releases the Depth Pro 2 Model Series
Source:Apple Machine Learning Research
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 21
Apple Machine Learning ResearchFirst-party
Apple Releases Depth Pro 2 Research on Monocular Metric Depth Estimation
Apple has introduced Depth Pro 2, a single scalable network that processes images, videos, and live camera feeds at their original resolution and estimates per-pixel depth in meters. The method combines metric accuracy, sharp object boundaries, and temporal consistency across frames, and the associated model, code, and weights have been released.
AI Trends