Depth Pro is Apple's foundation model for monocular depth estimation that produces metric-scale, high-resolution depth maps from a single image in under a second without requiring camera intrinsics.
Depth Pro — Sharp Monocular Metric Depth Estimation by Apple
Depth Pro is Apple's foundation model for monocular depth estimation that produces metric-scale, high-resolution depth maps from a single image in under a second without requiring camera intrinsics.
Instalación lista para agent
Este activo puede instalarse después de elegir el runtime, revisar el plan y ejecutar el comando correspondiente.
npx -y tokrepo@latest install 690fd92c-7913-11f1-9bc6-00163e2b0d79 --target codexEjecutar después de confirmar el plan con dry-run.
Discusión
Activos relacionados
Depth Anything V2 — Monocular Depth Estimation at Scale
Depth Anything V2 is a family of monocular depth estimation models that predict accurate relative depth maps from single RGB images, trained on a massive dataset of 62 million labeled images.
DINOv2 — Self-Supervised Visual Features by Meta
DINOv2 produces universal visual features via self-supervised learning on curated data, providing strong image representations for classification, segmentation, and depth estimation without fine-tuning.
ControlNet — Add Spatial Control to Diffusion Models
ControlNet lets you add precise spatial conditioning such as edge maps, depth, and pose to Stable Diffusion, giving fine-grained control over AI image generation.
Amass — In-Depth Attack Surface Mapping and Asset Discovery
An OWASP project for network mapping and external asset discovery using open source intelligence gathering and active reconnaissance techniques.