3D-CovDiffusion

3D-CovDiffusion checkpoints

Category-specific tensor-only policies for 3D-CovDiffusion: 3D-Aware Diffusion Policy for Coverage Path Planning.

• Project page: https://crystalccy1.github.io/3D-CovDiffusion/
• Paper: https://arxiv.org/abs/2510.03011
• Code: https://github.com/crystalccy1/3D-CovDiffusion
• Dataset: https://huggingface.co/datasets/ChenyuanC/3D-CovDiffusion-Train-Ready

The paper reports a jointly trained, category-agnostic model across benchmark geometries. This public model repository contains separately trained checkpoints for Windows, Cuboids, Shelves, and Containers and follows their checkpoint-producing saved configurations; see the code repository's paper-versus-release protocol boundary.

Released variants

Each root category contains the EMA policy selected by its original seed-42 run. raw/<category>/ contains the non-EMA state_dicts.model export used by the archived selected-visualization script. Here raw means policy weights before EMA, not raw dataset input or a Python/pickle checkpoint.

Every directory contains model.safetensors, config.yaml, and provenance metadata.

The score above is the run's prediction-conditioned weighted 6-D pose Chamfer used for top-k selection. It includes XYZ and orientation normal and is not the final XYZ-only PCD or the paper's three-seed test result.

Containers is a separate low-data experiment. ODAV4-S42 is released because it is referenced by the archived in-domain, OOD, and video evaluation scripts.

Evaluate

From the code repository:

bash scripts/create_locked_environment.sh 3dcov-cu117
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate 3dcov-cu117
export PYTHONNOUSERSITE=1
python reproduce.py prepare windows
python reproduce.py evaluate windows

prepare obtains the model and the pinned, train-ready Hugging Face data below one --artifact-root. The self-contained evaluation records include the exact model input, ground-truth trajectory, stroke grouping, and mesh geometry needed for rollout metrics; no raw-data archive or source-repository checkout is required at runtime.

Use evaluate all for every released EMA policy. To replay the selected non-EMA case and automatically verify its numeric result:

python reproduce.py infer windows

Rendering is optional:

python -m pip install --no-build-isolation --require-hashes \
  -r requirements/requirements-visualization-linux-py310-cu117.lock.txt
python reproduce.py infer windows --render

The PLY hash is a locked-environment render regression, not a requirement for numeric reproduction. The full checkpoint/config/test-index matrix and hashes are in docs/INFERENCE.md and configs/inference/seed42_selected_episodes.json in the code repository.

Format and integrity

• <category>/model.safetensors contains the complete EMA policy state.
• raw/<category>/model.safetensors contains the complete non-EMA policy state used for the selected-case replay.
• Both include action and point-cloud normalizer tensors.
• Optimizer state, Python/Dill training checkpoints, experiment logs, and machine-local paths are excluded.
• metrics.json records source run, epoch/step, historical selection score, source digest, release digest, and tensor-roundtrip validation.
• manifest.json and SHA256SUMS provide repository-wide integrity metadata.

Users never need to load the trusted historical pickle checkpoints; all public weights are safetensors.

Intended use and limitations

The policies generate ordered 6-DoF coverage-trajectory chunks from a 5,120-point observation and the previous 24-D action token (four ordered 6-DoF poses). They are research artifacts, not a certified motion-planning or robot- safety system. Validate collisions, kinematics, workcell constraints, and emergency behavior before physical deployment.

Only one selected seed-42 checkpoint is public per category. The paper's three-seed mean and standard deviation require the independent seed-123/456 checkpoints or their result JSON files.

License

To the extent the 3D-CovDiffusion authors hold the necessary rights, the released EMA and non-EMA model weights are licensed under CC BY 4.0. The grant covers model-weight files only; source code, datasets, the paper, website media, and third-party materials retain their separate terms. See MODEL_LICENSE.md and the repository's third-party notices.

Citation

@misc{chen2026_3dcovdiffusion,
  title  = {{3D-CovDiffusion}: 3D-Aware Diffusion Policy for Coverage Path Planning},
  author = {Chen, Chenyuan and Ding, Haoran and Ding, Ran and Liu, Tianyu
            and He, Zewen and Duan, Anqing and Nakamura, Yoshihiko},
  year   = {2026},
  eprint = {2510.03011},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url    = {https://arxiv.org/abs/2510.03011},
  note   = {Accepted at IROS 2026}
}