WorldFoundry
English中文

3D & 4D · monocular-depth-estimation · metric-depth-estimation · geometry-prior

Metric3D Prior

JUGGHM

Integrated as an independent metric-depth prior at worldfoundry/base_models/three_dimensions/depth/metric3d.

Runner verifiedUnified environmentmetric3d-prior

Build your run

Choose a recorded variant, then copy the exact setup or inspection command.

worldfoundry.pipeline
Taskmonocular-depth-estimation
Environmentworldfoundry-unified-cu128
DeviceCUDA 12.8
worldfoundry-eval evaluate \
  --mode model \
  --model-id metric3d-prior \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/metric3d-prior \
  --metric artifact_count \
  --json
01

Compatibility & versions

Manifest-backed recipe

Integration
integrated
Runner evidence
verified
Environment
worldfoundry-unified-cu128
Python
3.11
CUDA
CUDA 12.8
PyTorch
torch
Source revision
—
Checkpoint revision
—
Runtime profile
metric3d-prior
Pipeline binding
metric3d-prior
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.geometry_priors.pipeline_geometry_priors:Metric3DPriorPipeline
Backend stage
in_tree_geometry_prior_runtime
Runtime status
in_tree_runtime_wired
Driver status
compatible_unified_default
Environment kind
Unified environment
02

Install environment

The environment resolver reads the recorded profile and chooses the unified or dedicated environment shown here.

bash scripts/setup/model_env_install.sh --model metric3d-prior
Package constraints 4
  • torch
  • torchvision
  • torchaudio
  • xfuser
Conda packages 5
  • python=3.11
  • pip
  • ffmpeg
  • setuptools
  • wheel
03

Checkpoints & assets

Run the local check before allocating compute. Gated, private, and license fields below come directly from the checkpoint manifest.

worldfoundry-eval zoo model-download --model-id metric3d-prior --check-local --json
JUGGHM/Metric3D
Revision
—
License
—
Gated
—
Private
—
04

Launch & outputs

The generated command uses the shared evaluation boundary and writes durable result manifests and artifacts.

worldfoundry-eval evaluate \
  --mode model \
  --model-id metric3d-prior \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/metric3d-prior \
  --metric artifact_count \
  --json

Input contract

FieldRecorded contract
promptOptional
imageRequired
videoOptional
actionsmonocular_metric_depth

Artifact contract

Artifact kindFilename / path
generated_3d_assetmetric3d-prior.npz
05

Evidence & sources

Catalog integration, native-demo parity, and runner parity are independent records.

Integration
integrated
Runner evidence
verified
Native demo evidence
Not recorded
Validation imports
torch, torchvision, numpy, transformers, diffusers, xfuser, worldfoundry
Recipe provenance
worldfoundry/data/models/catalog/three_d_four_d/metric3d-prior.yamlGitHubhttps://github.com/YvanYin/Metric3DHugging Facehttps://huggingface.co/JUGGHM/Metric3D