1.7B Articulation Structure Checkpoint

Given a full-object point cloud, a target-part point cloud, and the object's candidate part list, this checkpoint predicts which parts move together with the target part.

Model details

Item Value
Internal task name group
Required geometry Object point cloud + target-part point cloud + candidate-part metadata
Training lineage 1.7B initialization โ†’ physical grounding โ†’ structure fine-tuning
Training data To be announced
Evaluation data To be announced
Tested Transformers version 4.51.0

Inputs and outputs

The object .npz must contain the regular point-cloud arrays and two additional candidate-part arrays:

point         float32 [N, 3]
color         uint8   [N, 3]
normal        float32 [N, 3]
part_names            [K]
part_centers           [K, 3]

part_names contains candidate part identifiers. part_centers contains their centers in the source coordinate frame and must be aligned with part_names. The target part must also be supplied as a separate point cloud.

The structured prediction is:

{"members": [0, 2, 3]}

Every returned member is selected from the supplied candidate identifiers.

Installation

Set CODE_REPO_URL to the URL of the anonymous source code repository.

git clone "$CODE_REPO_URL" source
cd source
python -m pip install -e .
bash scripts/install_cuda_extensions.sh

The model uses a custom Transformers architecture. Install the accompanying source code before loading the checkpoint; a generic transformers.pipeline is not supported.

Inference

Replace /path/to/checkpoint with the local checkpoint directory.

CUDA_VISIBLE_DEVICES=0 python inference_batch_articulation_structure.py \
  --model_path /path/to/checkpoint \
  --object_pcd examples/object_with_parts.npz \
  --part_pcd examples/part.npz \
  --output outputs/articulation_structure.json

For batch inference, pass a JSON list with --input_json. The source candidate metadata is retained in each output record for traceability and evaluation.

Evaluation

python -m eval articulation_structure PREDICTIONS \
  --output articulation_structure_metrics.json

Benchmark results are pending.

Intended use and limitations

This checkpoint is intended for research on articulation structure grounding and for proposing motion-coupled part groups in 3D assets. Its result depends on the completeness and correctness of the supplied candidate part decomposition.

Performance may degrade for missing or duplicated parts, inconsistent part identifiers, very fine or very coarse decompositions, nested mechanisms, sparse point clouds, or objects outside the training distribution. Validate the predicted grouping before constructing simulation constraints.

License

The model weights are released under the Creative Commons Attribution-NonCommercial 4.0 International license. Commercial use is not permitted under this license. The accompanying source code is licensed separately under Apache-2.0. See the included license for Qwen3 and Sonata attribution.

Downloads last month
-
Safetensors
Model size
2B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for anonymous-abc123/UniPhysGen-1.7B-Structure

Finetuned
Qwen/Qwen3-1.7B
Finetuned
(1,416)
this model