# Apple — Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth

- Company: Apple (apple.com)
- Announced: 2026-11-20
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://machinelearning.apple.com/research/depth-pro-2-monocular
- Record: https://forck.live/items/39377-depth-pro-2-sharp-and-temporally-consistent-metric-monocular-depth
- Subject: Machine Learning Research
- Open weights: yes
- Models affected: Depth Pro 2, Depth Pro, SHARP

Apple researchers present Depth Pro 2, a single network that estimates dense metric depth for both images and video at full resolution, and release a family of models with code and weights. The team says prior monocular depth methods trade off temporal consistency against boundary sharpness, with multi-frame methods favoring consistency and single-frame methods favoring sharpness. Depth Pro 2 is trained as one scalable network that processes images and video and predicts depth maps at native resolution, which the authors say lets it be metrically accurate, sharp and temporally consistent at once. Apple says the models outperform prior work on all of those dimensions and define a new Pareto frontier in metric accuracy, sharpness, temporal consistency and runtime. The release follows Depth Pro, a zero-shot metric monocular depth foundation model that Apple described in October 2024 as producing a 2.25-megapixel depth map in 0.3 seconds on a standard GPU.

## Evidence

Verbatim from https://machinelearning.apple.com/research/depth-pro-2-monocular:

> Authors Peiyun Hu, Marko Mihajlovic, Lyndon Duong, Lahav Lipson, Wei Dong, Amaël Delaunoy, Stephan R. Richter, Vladlen Koltun
> 
> 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 .
> 
> Related readings and updates.
> 
> December 13, 2025 research area Computer Vision , research area Methods and Algorithms conference ICLR
> 
> We present SHARP, an approach to photorealistic view synthesis from a single image.

---

Record: https://forck.live/items/39377-depth-pro-2-sharp-and-temporally-consistent-metric-monocular-depth
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
