Apple Releases Depth Pro 2 for Sharp and Temporally Consistent Monocular Depth
Apple introduces Depth Pro 2, a single scalable network that processes both images and video to predict metrically accurate depth maps at native resolution, simultaneously achieving boundary sharpness and temporal consistency. It requires no camera intrinsics metadata for absolute scale and produces a 2.25-megapixel depth map in 0.3 seconds on a standard GPU, with code and weights released openly.
Full Report
We present Depth Pro 2, an approach to estimating dense metric depth for images and video at full resolution. By analyzing prior methods for monocular depth estimation, we find that they commonly trade off temporal consistency and boundary sharpness: multi-frame methods favor consistency, single-frame methods favor sharpness. To overcome this trade-off, we train a single, scalable network that processes both images and video and predicts depth maps at native resolution. Depth Pro 2 produces depth maps that are metrically accurate, sharp, and temporally consistent all at once, outperforming prior work in all of these dimensions. We release a family of models that define a new Pareto frontier in terms of metric accuracy, sharpness, temporal consistency, and runtime.
We release code and weights here.
Depth Pro 2 estimates the depth of every pixel, in meters, from images taken with an ordinary camera. One network handles a single photo, a whole video, or a live camera feed, at the input’s full resolution. Its depth is sharp at object edges and steady from frame to frame.
Related readings and updates.
### Sharp Monocular View Synthesis in Less Than a Second
December 13, 2025research area Computer Vision, research area Methods and Algorithmsconference ICLR
We present SHARP, an approach to photorealistic view synthesis from a single image. Given a single photograph, SHARP regresses the parameters of a 3D Gaussian representation of the depicted scene. This is done in less than a second on a standard GPU via a single feedforward pass through a neural network. The 3D Gaussian representation produced by SHARP can then be rendered in real time, yielding high-resolution photorealistic images for nearby…
Read more### Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
October 9, 2024research area Computer Visionconference ICLR
We present a foundation model for zero-shot metric monocular depth estimation. Our model, Depth Pro, synthesizes high-resolution depth maps with unparalleled sharpness and high-frequency details. The predictions are metric, with absolute scale, without relying on the availability of metadata such as camera intrinsics. And the model is fast, producing a 2.25-megapixel depth map in 0.3 seconds on a standard GPU. These characteristics are enabled by…