Skip to content

Latest commit

 

History

History
114 lines (92 loc) · 6.02 KB

File metadata and controls

114 lines (92 loc) · 6.02 KB

Computer Vision Examples Monorepo

A Pixi workspace of computer vision applications, reusable libraries, and source-built dependencies. Runnable projects live under packages/ and compose shared features with package-specific dependencies in the root pixi.toml. Most runnable packages have a production environment (<name>) and a development environment (<name>-dev) with the same dependency solve.

The workspace platforms are linux-64, linux-aarch64, and osx-arm64, plus the named linux-64-cuda13 and linux-aarch64-cuda13 platforms that carry the CUDA 13.0 virtual packages for GPU environments. Each feature opts into its platforms explicitly, so most GPU packages are Linux-only; check the package README and its feature in pixi.toml before installing on macOS. See the "Platforms & lockfile" section of AGENTS.md for the full rules.

Quick start

  1. Install Pixi, then restart your shell:

    curl -fsSL https://pixi.sh/install.sh | sh
  2. Clone the workspace and install one development environment:

    git clone https://github.com/rerun-io/examples-monorepo.git
    cd examples-monorepo
    pixi install -e monoprior-dev --frozen
  3. Run that package's demo task from the repository root:

    pixi run -e monoprior-dev --frozen monoprior-relative-depth

Choose another package from the map below, then use its README or pixi task list -e <name> to find its demo task. Tasks with download dependencies fetch their example assets on first run.

Optional: direnv

The root .envrc activates dev. Package directories that contain their own .envrc default to <name>-dev, so after installing direnv you can opt in per directory:

cd packages/monoprior
direnv allow
pytest -q

Set PIXI_ENV in a gitignored .envrc.local to override a directory's default.

Package map

Package What it contains
arkitscenes-download ARKitScenes downloader and ingest pipeline that emits layered Rerun recordings. Try pixi run -e arkitscenes-download arkitscenes-download-sample for a 5-sequence demo.
asmk Pixi-build recipe for the ASMK image-retrieval dependency used by MASt3R-SLAM.
dpretrieval Pixi-build recipe for a DBoW2/pybind11 image-retrieval extension used by DPVO.
dpvo Deep Patch Visual Odometry with Rerun and Gradio integrations.
egoexo-forge Rerun and Gradio tools for egocentric and exocentric human datasets.
gsplat-rust-renderer GPU Gaussian-splat viewer implemented as a custom Rerun visualizer. See its README.
live-rerun Zero-transcode live H.264/H.265 sensor streaming into Rerun.
mamma Streaming multiview body capture from decode through SMPL-X fitting and Rerun logging.
mast3r Pixi-build recipe bundling MASt3R, DUSt3R, and CroCo.
mast3r-slam Dense visual SLAM built on MASt3R reconstruction priors.
monoprior Monocular relative depth, metric depth, surface-normal, and calibration tools.
mv-api Full egocentric/exocentric multiview processing for raw HOCap datasets.
posekit One model API for human perception networks (detect, pose, segment, re-ID) over torch/onnx/tensorrt backends.
prompt-da Prompt Depth Anything depth completion for Polycam captures and ARKitScenes catalog segments.
pysfm COLMAP/pycolmap structure-from-motion with Rerun visualization.
pyvrs-viewer VRS-to-Rerun conversion with compressed video and sensor streams.
robocap-slam Multicamera visual odometry and SLAM using NVIDIA cuVSLAM.
sam2-streaming Vendored, inference-only SAM2 fork with frame streaming and bounded-memory banks.
sam3 Text-conditioned SAM3 image and video segmentation with Rerun.
sam3d-body Promptable SAM3D Body reconstruction and visualization playground.
sapiens-coco133-pose COCO-133 human pose pipelines using Sapiens2 or RTMLib backends.
sapiens2-pose Top-down 308-keypoint human pose estimation with Rerun.
simplecv Shared Python utilities for datasets, geometry, video, and Rerun logging.
slam-evals VSLAM benchmark ingestion and browsing through a Rerun catalog.
vistadream Single-image 3D reconstruction and Gaussian-scene tooling.
wilor-nano Hand detection and 3D hand-pose estimation with Rerun logging.

Build-only and vendored packages do not necessarily have standalone root environments or demo tasks; their role is described in the second column.

Conventions

  • Root-managed runnable packages generally use <name> for production and <name>-dev for development. The [environments] table in pixi.toml is the source of truth.

  • Development environments expose the canonical lint, typecheck, deadcode, and tests tasks:

    pixi run -e robocap-slam-dev --frozen lint
    pixi run -e robocap-slam-dev --frozen typecheck
    pixi run -e robocap-slam-dev --frozen deadcode
    pixi run -e robocap-slam-dev --frozen tests
  • Prefer pixi run --frozen and pixi install --frozen while dependencies are unchanged. Omit --frozen only when intentionally updating the solve and lockfile.

  • List the tasks available in an environment with pixi task list -e <name> or pixi task list -e <name>-dev.

For agent and contributor documentation — architecture, platform rules, adding a new package, Rerun version policy, and known issues — see AGENTS.md.