ArtCrafter: Feed-Forward Generation of Articulated 3D Object with Analytic Joint Derivation
Organizations: Qualcomm AI Research
Abstract
Articulated 3D assets are essential for robotic simulation and training, yet their generation from casual images poses a key challenge: recovering part geometry and kinematics that remain mutually consistent. We present ArtCrafter, a novel feed-forward generative model for controllable generation of articulated 3D objects from a pair of images, one depicting the object in the rest state and the other in the open state. At the core of ArtCrafter is a DiT-based generative model that jointly produces part-level meshes for both articulation states in a single forward pass. Inspired by Slot Attention, its denoising process operates on a slot layout comprising one shared base slot and paired rest/open slots, encouraging each pair to bind to the same kinematic part. To ensure geometrically consistent and disjoint part generation, we introduce Triplet Attention to enforce cross-state geometric consistency between paired rest/open slots anchored through the shared base slot, and a repulsion loss on decoded part point clouds to prevent inter-part penetration throughout denoising. Given the resulting paired meshes, URDF joint parameters---type, axis, origin, and range---are derived analytically from the rigid transformation between each rest/open pair, providing an interpretable alternative to learned joint-parameter regression. Extensive experiments on both in-distribution and out-of-distribution datasets demonstrate that ArtCrafter outperforms existing method under the same dual-state setting in geometry quality and articulation precision, while remaining competitive with methods operating under different input settings and paradigms.
Figures & tables
| Paradigm | Single-state | Dual-state | Multi-view / multi-state |
| Retrieval | Articulate-Anything Le et al. (2025) , SINGAPO Liu et al. (2025a) , URDFormer Chen et al. (2024) | DIPO Wu et al. (2026b) | — |
| Segmentation | URDF-Anything Li et al. (2026b) | — | URDF-Anything Li et al. (2026b) |
| Optimization | — | — | PARIS Liu et al. (2023) , ArtGS Liu et al. (2025b) , LARM Yuan et al. (2025) , FreeArt3D Chen et al. (2025a) , REArtGS Wu et al. (2026a) |
| Generation | PAct Liu et al. (2026) , SPARK He et al. (2025b) , URDF-Anything+ Wu et al. (2026c) , PhysX-Anything Cao et al. (2025) | ArtCrafter (ours) | ART Li et al. (2025d) |
| Method | Geometry | Kinematics | |||||
| Whole-Object | Part | Axis Err. | Origin Err. | Limit Err. | |||
| CD | F1 | CD | F1 | ||||
| URDFormer † Chen et al. (2024) | 0.286 | 0.413 | 0.354 | 0.389 | 1.071 | 0.504 | 0.882 |
| FreeArt3D Chen et al. (2025a) | 0.113 | 0.426 | 0.078 | 0.413 | 0.668 | 0.330 | 1.662 |
| PhysX-Anything † Cao et al. (2025) | 0.068 | 0.715 | 0.076 | 0.697 | 0.191 | 0.103 | 0.532 |
| DIPO Wu et al. (2026b) | 0.047 | 0.289 | 0.044 | 0.276 | 0.309 | 0.107 | 1.158 |
| Method | Geometry | Kinematics | |||||
| Whole-Object | Part | Axis Err. | Origin Err. | Limit Err. | |||
| CD | F1 | CD | F1 | ||||
| PhysX-Anything Cao et al. (2025) | 0.076 | 0.274 | 0.027 | 0.382 | 1.148 | 0.542 | 1.312 |
| FreeArt3D Chen et al. (2025a) | 0.131 | 0.135 | 0.101 | 0.163 | 0.831 | 0.419 | 1.182 |
| DIPO Wu et al. (2026b) | 0.071 | 0.158 | 0.072 | 0.179 | 1.059 | 0.480 | 0.906 |
| ArtCrafter (w/ VLM) | 0.047 | 0.352 | 0.052 | 0.340 | 0.918 | 0.463 | 1.308 |
| Cross-state part enforcement | Geo. Reg. | Whole-Object | Part | ||||
| Variant | Triplet attn | Pair-wise Attn | CD | F1 | CD | F1 | |
| Base | 0.022 | 0.579 | 0.013 | 0.608 | |||
| + Geo. Reg. | 0.014 | 0.583 | 0.012 | 0.614 | |||
| + Triplet attn | 0.015 | 0.609 | 0.011 | 0.639 | |||
| + Pair-wise Attn | 0.017 | 0.580 | 0.013 | 0.592 | |||
| Ours | 0.014 | 0.626 | 0.010 | 0.646 | |||
| Method | Axis Err. | Origin Err. | Limit Err. |
| ArtCrafter (Learned Joint Head) | 1.049 | 0.322 | 2.142 |
| ArtCrafter (Registration) | 0.181 | 0.082 | 0.593 |
Appendix figures & tables11 assets
Supplementary material from the paper’s appendix.
Appendix
| Statistic | Count |
| Objects | 2,614 |
| Categories | 10 |
| Parts | 5,990 |
| Joints | 3,376 |
| Revolute joints | 3,217 |
| Prismatic joints | 159 |
| Number of parts | Count | Proportion |
| 2 | 1,962 | 75.1% |
| 3 | 542 | 20.7% |
| 4 | 109 | 4.2% |
| 5 | 1 | 0.04% |
| TOTAL | 2,614 | 100% |
| Category | Train | Val | Test | Total |
| Dishwasher | 200 | 10 | 14 | 224 |
| Display | 253 | 13 | 24 | 290 |
| Door | 40 | 2 | 5 | 47 |
| Faucet | 575 | 30 | 49 | 654 |
| Knife | 23 | 1 | 3 | 27 |
| Laptop | 408 | 21 | 41 | 470 |
| Statistic | OOD test set |
| Objects | 187 |
| Categories | 46 |
| Parts | 537 |
| Joints | 350 |
| Rev. joints | 280 |
| Pris. joints | 70 |
| Num parts | Count | % |
| 2 | 72 | 38.5% |
| 3 | 77 | 41.2% |
| 4 | 28 | 15.0% |
| 5 | 10 | 5.3% |
| TOTAL | 187 | 100% |
| Method | Part Geometry | Whole-Object Geometry | Kinematics | |||||
| F-score | CD | F-score | CD | Axis Err | ||||
| Std. | Pen. | Std. | Pen. | Std. | Pen. | |||
| PhysX-Anything | 0.382 | 0.317 | 0.027 | 0.091 | 0.274 | 0.076 | 1.148 | 1.341 |
| FreeArt3D | 0.163 | 0.146 | 0.101 | 0.143 | 0.135 | 0.131 | 0.831 | 1.226 |
| DIPO | 0.184 | 0.157 | 0.074 | 0.129 | 0.158 | 0.071 | 1.059 | 1.174 |
| ArtCrafter (w/ VLM) | 0.340 | 0.325 | 0.052 | 0.070 | 0.352 | 0.047 | 0.918 | 0.974 |
| Time | RAM | VRAM | |
| Training (4 H100s) | 3 hrs 50 mins | 20 GB | 43.2 GB |
| Prediction (1 H100) | 22.4 sec | 10.3 GB | 10.5 GB |
| Method | Inference time | Details |
| DIPO | 12.3 sec | |
| FreeArt3D | 606 sec | |
| PhysX-Anything | 395 sec | |
| ArtCrafter (Ours) | 22.4 sec | DINO+DiT+VAE: 18.7 sec, Registration: 3.7 sec |
| Method | Parts F-Score ( ) | Parts CD ( ) | Whole F-Score ( ) | Whole CD ( ) |
| ArtCrafter (with fixed ) | 0.640 | 0.00897 | 0.686 | 0.00631 |
| ArtCrafter | 0.716 | 0.006 | 0.732 | 0.006 |