Recent advances in point cloud In-Context Learning (ICL) have demonstrated strong multitask capabilities. Existing approaches typically adopt a Masked Point Modeling (MPM)-based paradigm for point cloud ICL. However, MPM-based methods directly predict the target point cloud from masked tokens without leveraging geometric priors, requiring the model to infer spatial structure and geometric details solely from token-level correlations via transformers. Additionally, these methods suffer from a training-inference objective mismatch, as the model learns to predict the target point cloud using target-side information that is unavailable at inference time. To address these challenges, we propose DeformPIC, a deformation-based framework for point cloud ICL. Unlike existing approaches that rely on masked reconstruction, DeformPIC learns to deform the query point cloud under task-specific guidance from prompts, enabling explicit geometric reasoning and consistent objectives. Extensive experiments demonstrate that DeformPIC consistently outperforms previous state-of-the-art methods, achieving reductions of 1.6, 1.8, and 4.7 points in average Chamfer Distance on reconstruction, denoising, and registration tasks, respectively. Furthermore, we introduce a new out-of-domain benchmark to evaluate generalization across unseen data distributions, where DeformPIC achieves state-of-the-art performance.
Figures & tables
Figure 2: Overall framework of DeformPIC. Our model consists of two core components. The Deformation Extraction Network (DEN) extracts the geometric transformation from an example pair (prompt input→prompt target) into a task embedding. This embedding then modulates the Deformation Transfer Network (DTN), thereby guiding it to apply the same transformation to a new query input to produce the final prediction. The entire network is trained by minimizing the Chamfer Distance [ 9 ] against the ground truth.
Models
Venues
Part.
Reconstruction CD ↓
Denoising CD ↓
Registration CD ↓
mIoU ↑
L1
L2
L3
L4
L5
Avg.
L1
L2
L3
L4
L5
Avg.
L1
L2
L3
L4
L5
Avg.
Task-Specific Models: trained separately for single task
PointNet [ 32 ]
CVPR’17
77.5
3.7
3.7
3.8
3.9
4.1
3.9
4.1
4.0
4.1
4.0
4.2
4.1
5.3
5.9
6.9
7.7
8.5
6.9
DGCNN [ 44 ]
TOG’19
76.1
3.9
3.9
4.0
4.1
4.3
4.0
4.7
4.5
4.6
4.5
4.7
4.6
6.2
6.7
7.3
7.4
7.7
7.1
PCT [ 14 ]
CVM’21
79.5
2.4
2.4
2.5
2.6
3.0
2.6
2.3
2.2
2.2
2.2
2.3
2.2
5.3
5.7
6.3
6.9
7.2
6.3
ACT [ 8 ]
ICLR’23
81.2
2.4
2.5
2.3
2.5
2.8
2.5
2.2
2.3
2.2
2.3
2.5
2.3
5.1
5.6
5.9
6.0
7.0
5.9
Table 1: Comparison with state-of-the-art methods on the ShapeNet In-Context dataset [ 10 ] . For reconstruction, denoising, and registration, we report Chamfer Distance [ 9 ] loss ( ×1000 ). For part segmentation (Part.), we report mIoU. Since PIC [ 10 ] does not provide the details of specific multi-task heads, we tested with our own designed multi-task heads, which are marked with † . Bold: the best results. Underline: the second-best results.
Figure 3: Qualitative comparison on ShapeNet In-Context dataset. From left to right: input point clouds, PIC-Cat [ 10 ] results, our DeformPIC results, and ground truth. Our method achieves better geometric detail preservation, improved structural coherence, and fewer visual artifacts across diverse tasks.
Models
Rec. CD ↓
Den. CD ↓
Reg. CD ↓
M.
S.
M.
S.
M.
S.
Multitask Models
Point-MAE [ 30 ]
5.0
5.3
8.1
9.6
38.2
26.1
ReCon [ 33 ]
5.7
5.8
9.5
10.9
37.9
41.9
PCP-MAE [ 54 ]
5.7
6.0
9.8
11.2
37.6
42.8
UniPre3D [ 46 ]
5.5
5.6
12.6
14.8
38.7
42.9
Table 2: Comparison of generalization ability with state-of-the-art methods on the ModelNet40 In-Context (M.) and ScanObjectNN In-Context (S.) datasets. We report task-averaged Chamfer Distance [ 9 ] ( ×1000 ).
Model
Consis.
DTN
DEN
Rec.
Den.
Reg.
PIC-Cat
✗
✗
✗
4.3
5.3
14.1
✓
✗
✗
3.2
4.0
3.5
Ours
✓
✓
✗
3.1
3.8
2.9
✓
✓
✓
2.7
3.5
2.0
Table 3: Ablation Study of DeformPIC on ShapeNet In-Context. We report the task-averaged Chamfer Distance ( ×1000 ) for the reconstruction, denoising, and registration tasks.
Figure 4: Task Feature Visualization of DeformPIC on the ShapeNet / ModelNet40 / ScanObjectNN In-Context datasets. We use t-SNE [ 29 ] to reduce the dimensionality of the task features to a 2D space and visualize the distributions of task features.
Appendix figures & tables8 assets
Supplementary material from the paper’s appendix.
Appendix
Models
Flops(G)
Param.(M)
Reconstruction CD ↓
Denoising CD ↓
Registration CD ↓
L1
L2
L3
L4
L5
Avg.
L1
L2
L3
L4
L5
Avg.
L1
L2
L3
L4
L5
Avg.
PIC-Cat [ 10 ]
11.31
28.91
3.2
3.6
4.6
4.9
5.5
4.3
3.9
4.6
5.3
6.0
6.8
5.3
10.0
11.4
13.8
16.9
18.6
14.1
PIC-Sep [ 10 ]
8.14
28.91
4.7
4.3
4.3
4.4
5.7
4.7
6.3
7.2
7.9
8.2
8.6
7.6
8.6
9.2
10.2
11.3
12.4
10.3
DeformPIC- 12d
5.33
40.48
2.1
2.2
2.4
2.7
3.9
2.7
2.8
3.3
3.5
3.7
3.8
3.4
1.8
1.8
1.9
1.9
2.0
1.9
DeformPIC- 8d
4.87
29.84
2.2
2.3
2.5
2.8
3.9
2.7
2.8
3.3
3.6
3.8
3.9
3.5
1.9
1.9
1.9
2.0
2.1
2.0
Appendix
Table 4: Comparison of model variants in terms of computational complexity, and in-context performance in ShapeNet In-Context [ 10 ] .
Models
Rec.
Den.
Reg.
F-score@ τ
F-score@ τ
F-score@ τ
PIC-Cat [ 10 ]
38.36
33.06
26.98
PIC-Sep [ 10 ]
42.78
32.86
41.57
DeformPIC- 8d
57.98
49.95
66.04
Appendix
Table 5: Comparison with state-of-the-art methods in F-score@ τ ( τ=0.001 ) on ShapeNet In-Context [ 10 ] .
Models
Rec. EMD
Den. EMD
Reg. EMD
PIC-Cat [ 10 ]
56.30
52.89
75.14
PIC-Sep [ 10 ]
60.83
65.27
64.28
DeformPIC- 8d
37.01
47.32
24.05
Appendix
Table 6: Comparison with state-of-the-art methods in EMD ( ×1000 ) on ShapeNet In-Context [ 10 ] .
Encoding Strategies
Rec. CD ↓
Den. CD ↓
Reg.CD ↓
Static ( Predict Task ID )
3.2
4.0
9.9
Dynamic ( Predict Task Token )
2.7
3.5
2.0
Appendix
Table 7: Static vs. Dynamic Encoding on DEN.
Figure 5: Visualization results on registration task compared with the PIC [ 10 ] and our approach.
Figure 6: Visualization results on reconstruction task compared with the PIC [ 10 ] and our approach.
Figure 7: Visualization results on denoising task compared with the PIC [ 10 ] and our approach.
Figure 8: Visualization results on part segmentation task compared with the PIC [ 10 ] and our approach.