WorldFoundry
English中文

3D & 4D · camera-calibration · gravity-estimation · geometry-prior

GeoCalib Prior

cvg

Integrated as an independent camera-calibration prior at worldfoundry/base_models/three_dimensions/general_3d/geocalib.

Runner verifiedUnified environmentgeocalib-prior

Build your run

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

worldfoundry.pipeline
Taskcamera-calibration
Environmentworldfoundry-unified-cu128
DeviceCUDA 12.8
worldfoundry-eval evaluate \
  --mode model \
  --model-id geocalib-prior \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/geocalib-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
geocalib-prior
Pipeline binding
geocalib-prior
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.geometry_priors.pipeline_geometry_priors:GeoCalibPriorPipeline
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 geocalib-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 geocalib-prior --check-local --json

No checkpoint repository is recorded in the catalog manifest.

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

Input contract

FieldRecorded contract
promptOptional
imageRequired
videoOptional
actionscamera_calibration

Artifact contract

Artifact kindFilename / path
generated_3d_assetgeocalib-prior.json
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/geocalib-prior.yamlGitHubhttps://github.com/cvg/GeoCalib