- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper aims to equip existing 3D meshes with the information needed for interaction. The authors propose an automated annotation pipeline, UniPhys, and use it to construct a training dataset of approximately 40,000 objects and UniPhys-Bench, a benchmark with manually verified annotations for motion-relevant parts. Building on these resources, they train UniPhysGen, which uses Sonata to encode point clouds of the full object and a target part, and Qwen3-1.7B to predict part-level physical properties, joint parameters, motion dependencies, and object-level properties.
Critical strengths
-
The data resources are a notable contribution of this work. UniPhys-40K covers 3D assets from multiple sources with diverse part decompositions, providing both articulation and physical property annotations. UniPhys-Bench has undergone manual inspection and correction. The authors commit to releasing the annotations for both datasets and the pretrained models, which could benefit the research community.
-
The authors conduct targeted experiments on rotation augmentation, part decomposition granularity, and positional encoding, and use human evaluation to assess annotation quality before and after simulation-based verification. These results provide empirical support for the effectiveness of the pipeline and the robustness of the model.
Critical weaknesses
-
The paper’s clearest contributions lie in its automated annotation pipeline and data resources, while the novelty of the model itself is relatively limited. PhysX-3D and PhysForge already incorporate material, functional, and kinematic information into physical asset modeling, and Articulate AnyMesh has explored constructing articulated structures from raw meshes. The methodological novelty of this work rests on its treatment of heterogeneous part decompositions. However, the SO(3) data augmentation, spherical parameterization, and shared global positional encoding emphasized in the paper mainly improve rotational generalization, directional representation, and spatial correspondence between parts and the full object. The paper does not sufficiently substantiate how these designs resolve ambiguities in mechanical interpretation arising from variations in part granularity and incomplete structures.
-
It is unclear what the physical annotations are intended to represent and whether the evaluation reflects this objective. The paper treats numerical values obtained through VLM annotation and human plausibility checks as a single set of reference values and evaluates predictions using attribute-level errors. Closer agreement with these values does not necessarily imply greater physical accuracy. The authors provide human plausibility assessments based on motion videos and demonstrations of robotic interaction, but they do not report part-level interaction success rates or the overall proportion of physically executable assets produced by the model.
Questions for authors
Could the authors share additional interaction videos after the double-blind review process?
4 comments
To Reviewer jSjN (Part 2/3)
Response to Weaknesses 2: Physical Annotation Validity and Simulation Evaluation.
Weaknesses 2:
The evaluation relies on attribute-level agreement with VLM-generated, human-verified reference values, which may not fully reflect physical validity. The paper lacks quantitative evidence of part-level interaction success and overall asset executability.
Response:
We thank the reviewer for this important concern. As clarified in Section 3.1 (Lines 188–191), our objective is to establish physically plausible, internally consistent, and simulation-ready physical configurations for existing virtual 3D assets. UniPhys-Bench annotations undergo human verification and correction, including refinement of part decomposition and verification of articulation parameters, materials, densities, friction coefficients, and masses.
To further assess physical validity beyond numerical agreement with reference annotations and the qualitative Isaac Sim demonstrations in Figure 8, we conducted additional quantitative experiments evaluating articulation plausibility and part-level simulation interaction success.
Specifically, we randomly selected 50 UniPhys-Bench assets, comprising 488 parts and 124 movable parts. We rendered front-view images and used them as inputs to PhysX-3D and PhysX-Anything to generate complete 3D assets with physical annotations, while UniPhysGen directly operated on the original meshes.
Since the assets generated by PhysX-3D and PhysX-Anything differ from the original meshes in geometry, scale, and part decomposition, direct numerical comparison of joint axes and pivots is not reliable. We therefore adopted a unified three-level human evaluation protocol for articulation parameters: 2 (Correct) indicates physically reasonable motion; 1 (Partially Correct) indicates generally plausible motion with visible deviations; and 0 (Incorrect) indicates implausible motion or failure to achieve the intended articulation. We additionally evaluated part-level simulation interaction success through standardized physical interaction tests.
Table R18. Articulation plausibility and part-level simulation interaction success.
| Method | Joint Type Acc. ↑ | Axis Score ↑ / 2 | Pivot Score ↑ / 2 | Limit Score ↑ / 2 | Interaction Success Rate ↑ |
|---|---|---|---|---|---|
| UniPhysGen (Ours) | 87.90% | 1.556 | 1.565 | 1.605 | 69.35% (86/124) |
| PhysX-Anything | 60.00% | 1.227 | 1.067 | 0.760 | 37.33% (28/75) |
| PhysX-3D | 52.50% | 0.625 | 0.658 | 0.716 | 26.72% (31/116) |
Interaction Success Rate is measured over each method's evaluated movable parts, rather than all 124 ground-truth movable parts.
To further assess structural completeness, we matched the generated movable parts to the corresponding ground-truth parts and measured how many original movable parts were successfully recovered.
Table R19. Ground-truth movable-part matching performance.
| Method | Scored Motion Parts | GT Motion-Part Match Rate ↑ |
|---|---|---|
| UniPhysGen (Ours) | 124 | 100.00% (124/124) |
| PhysX-Anything | 75 | 22.58% (28/124) |
| PhysX-3D | 116 | 59.68% (74/124) |
UniPhysGen preserves the original part decomposition by operating directly on the input meshes, whereas image-to-3D generation methods must reconstruct the movable components.
We also evaluated intrinsic physical properties by matching corresponding components between the generated assets and the ground-truth assets.
Table R20. Intrinsic physical property comparison.
| Method | Material Accuracy ↑ | Density ALDE ↓ | Affordance MAE ↓ |
|---|---|---|---|
| PhysX-3D | — | 0.888 | — |
| PhysX-Anything | 67.21% | 0.741 | 1.656 |
| UniPhysGen (Ours) | 77.05% | 0.354 | 1.148 |
Metrics are computed over corresponding evaluable components; unavailable predictions are marked with “—”.
UniPhysGen achieves the highest part-level interaction success rate (69.35%), compared with 37.33% for PhysX-Anything and 26.72% for PhysX-3D. It also achieves stronger intrinsic physical property predictions on the evaluated metrics. These results provide quantitative evidence of simulation executability beyond agreement with reference annotations, while highlighting the importance of preserving the original articulated structure.
Together, these experiments provide quantitative evidence of articulation plausibility and part-level simulation executability beyond attribute-level agreement with reference annotations, while highlighting the practical advantage of grounding physical semantics directly on existing 3D geometry without regenerating the original asset.
To Reviewer jSjN (Part 3/3)
Response to Question: Additional Interaction Videos and Open-Source Availability
Question 1:
Could the authors share additional interaction videos after the double-blind review process?
Response:
Yes. We have recorded and released additional simulation interaction videos in NVIDIA Isaac Sim, demonstrating the physical interactions of our annotated 3D assets.
- Interaction Videos: https://huggingface.co/datasets/anonymous-abc123/Uniphys-Bench/tree/main/interaction_videos
Furthermore, we are committed to fully open-sourcing the UniPhys project. We have already anonymously released the complete codebase (UniPhys Pipeline and UniPhysGen), model weights, and UniPhys-Bench:
- Code (UniPhys Pipeline & UniPhysGen): https://github.com/anonymous-abc123/anonymous-code
- Model Weights: https://huggingface.co/collections/anonymous-abc123/model-weights
- UniPhys-Bench: https://huggingface.co/datasets/anonymous-abc123/Uniphys-Bench
The full UniPhys-40K training dataset has also been prepared and will be released publicly.
Revision Summary and Updated Manuscript
Revision Summary and Updated Manuscript
We thank the reviewer for the constructive feedback. We have uploaded a revised manuscript incorporating additional experiments and clarifications to address your concerns. The main revisions are summarized below:
-
Methodological Contributions and Model Architecture (Section 5.2 and Appendix F.4). We have added controlled comparisons with Sonata + Motion Head and UniPhysGen + Regression Head, providing further evidence for the effectiveness of our LLM-based architecture and token-based articulation parameter prediction beyond the shared 3D encoder and training data.
-
Generalization to Generated 3D Assets (Section 5.3 and Appendix F.6). We have incorporated additional experiments on TRELLIS 2.0-generated meshes, evaluating articulation semantics and intrinsic physical properties under variations in generated geometry and part decomposition.
-
Physical Validity and Simulation Interaction (Section 5.4 and Appendix F.7). We have added quantitative comparisons with PhysX-3D and PhysX-Anything, including articulation plausibility, movable-part recovery, and intrinsic physical properties. Importantly, we report part-level simulation interaction success rates, providing quantitative evidence of physical executability beyond attribute-level agreement and qualitative demonstrations.
The detailed experimental results and evaluation protocols are provided in Appendix F, with corresponding summaries and references in the main text.
We appreciate the reviewer's constructive feedback.
To Reviewer jSjN (Part 1/3)
Response to Weaknesses 1 : Methodological Contributions
Weaknesses 1:
Response:
We thank the reviewer for the constructive feedback. We clarify the conceptual and methodological contributions of UniPhys and UniPhysGen, and provide additional experimental evidence on generalization to heterogeneous geometry.
Our work addresses a fundamental challenge in 3D physical understanding: How can we ground existing 3D assets with diverse geometries and part decompositions in a unified physical semantic framework, without assuming canonical orientations, predefined articulation structures, or geometry regeneration?
To address this challenge, we introduce two complementary methodological contributions. UniPhys is a scalable geometry-aware annotation framework integrating physical semantic reasoning, geometry-constrained candidate generation, and simulation-based consistency verification. UniPhysGen directly learns physical semantics from native 3D point clouds, leveraging shared object-part geometric representations to infer articulation semantics and intrinsic physical properties across heterogeneous 3D structures.
Unlike PhysX-3D and PhysForge, which focus on image-conditioned generation of physically grounded 3D assets, UniPhysGen directly grounds physical semantics on existing 3D meshes with heterogeneous part decompositions, without regenerating their geometry. Articulate AnyMesh similarly aims to construct articulated assets from input meshes, but it re-segments movable parts and reconstructs their articulation structures, with optional geometry completion. Consequently, its output is a newly constructed articulated asset rather than a direct physical annotation of the original mesh and its existing part decomposition.
In contrast, UniPhysGen preserves the original geometry and part decomposition while recovering comprehensive physical properties, including articulation parameters, material, density, friction, scale, mass, and affordance. This distinction is important for real-world 3D asset repositories, where the same functional object may have different part granularities, incomplete structures, or manually defined decompositions. Nevertheless, we conducted additional quantitative comparisons with PhysX-3D and PhysX-Anything to evaluate articulation plausibility and simulation interaction success, as detailed in our response to Weakness 2.
Our methodological contribution lies in integrating shared object-part geometric representations with unified physical-semantic learning across heterogeneous 3D structures. Specifically, shared object-part representations provide geometric context for interpreting individual parts relative to the complete object, while SO(3) augmentation and spherical parameterization primarily improve orientation robustness. Table 4 demonstrates robustness to controlled variations in part grouping, while our additional evaluation on TRELLIS 2.0-generated assets provides further evidence of generalization to unfamiliar generated geometry.
Table R17. UniPhysGen performance on TRELLIS 2.0-generated assets.
We evaluated UniPhysGen on 32 TRELLIS 2.0-generated assets, containing 387 parts, including 73 movable parts (21 prismatic and 52 revolute). Reference annotations were first generated using our UniPhys Pipeline and subsequently inspected and corrected by human annotators before evaluation. Articulation metrics cover all 73 movable parts, while part-level physical metrics are computed over 382 valid predictions out of 387 annotated parts.
The results demonstrate that UniPhysGen maintains strong articulation prediction performance on generated geometry, including 91.78% Joint Type Accuracy and 12.05° Axis Error. Together with Table 4, these findings support its robustness to variations in geometric structure and part decomposition, while also identifying upstream segmentation quality as a remaining limitation.