Model

Depth Anything V2

Estimate a dense depth field from a single ordinary camera, with no stereo rig.

shipped Monocular Depth DepthSpatialCUDA

Overview

Depth Anything V2 predicts relative inverse-depth (disparity) per frame, larger = nearer. Overseer normalises it to [0,1], temporally median-fuses several frames to suppress monocular noise on the static scene, and back-projects it through a pinhole model to lift the frame into 3D. The depth field also drives the depth-locked tactical radar.

RoleMonocular Depth
Expected latency~120–400 ms / frame (Large tier, GPU); cached for the static scene
Hardware requirementsNVIDIA GPU strongly recommended
Memory requirements~2–4 GB VRAM (tier dependent)

Inputs & Outputs

Inputs
  • RGB frame
  • Working resolution
  • Fusion frame count
Outputs
  • Normalised disparity grid (float32)
  • Point cloud (with RGB)
  • Ground / background depth

Advantages & Limitations

Advantages

  • No calibration or stereo needed
  • Clean, temporally stable geometry
  • Great zero-shot generalisation across scenes

Limitations

  • Relative, not metric, without calibration
  • Reflective / transparent surfaces are hard
  • Heavier than detection, run periodically, not every frame

Example outputs

Configuration

Keys in config/default.yaml that govern this model.

KeyDefault
spatial.enabledtrue
spatial.input_width640
spatial.fuse_frames3
spatial.fov_deg60

Benchmarks

Placeholder

Benchmark figures below are illustrative and awaiting a standardised harness. Treat them as placeholders.

BenchmarkDatasetMetricValueHardware
δ<1.25NYU (ref)accuracy~0.98reference
Scene depth640pxms~240RTX 3060