Robust 3D point-cloud recognition is critical for robotics, mapping, and urban sensing, yet point-cloud classifiers often suffer performance drops under domain shifts caused by sensor changes, environmental variation, and acquisition artifacts. Many existing adaptation methods are difficult to deploy in practice because they require access to source data or the internal parameters of the source model, which may be restricted by privacy, licensing, or security constraints. We present 3D-BBDA, a backpropagation-free black-box domain adaptation framework that adapts a source-trained predictor to unlabeled target data using only black-box outputs. Our method performs pseudo-label guided prototype-based alignment and employs a weighted prediction module to fuse source logits with alignment logits, reducing sensitivity to noisy pseudo-labels. To stabilize prototype memory when pseudo-label coverage is incomplete, we construct a Gaussian-perturbed prototype prior from unlabeled target predictions and use it as a fallback for missing or unreliable class prototypes during alignment. Experiments on four corrupted 3D benchmarks demonstrate consistent improvements over strong baselines. On ModelNet-40C, 3D-BBDA achieves mean errors of 32.08% (PointNet) and 29.62% (GDANet), outperforming Source-only (35.88% / 34.03%) and BFTT3D (33.78% / 32.36%). 3D-BBDA requires only a single forward pass with no gradient updates making it suitable for real-time, privacy-preserving deployment in transferable 3D recognition pipelines. Project page is available at https://visdomlab.github.io/3D_BBDA
Figures & tables
Figure 1: Overview of the BBDA setting for 3D point cloud data. A pretrained source model acts as a black-box predictor and uses target data for adaptation.
Setting
Source data
Model internals
Target BP
Source-free
No
Allowed
Allowed
Black-box
No
No
Allowed
Backprop.-free
Allowed
Allowed
No
3D-BBDA
No
No
No
Table 1: Top: distinction between source-free, black-box, and backpropagation-free adaptation constraints. “Allowed” means the setting alone does not prohibit that access. Bottom: key differences between BFTT3D and 3D-BBDA.
Figure 2: Overview of 3D-BBDA, where target features from a non-parametric network are aligned via prototype generation and shared-subspace alignment. A Gaussian-perturbed prototype prior completes missing class prototypes, and final predictions fuse source and alignment outputs via weighted prediction.
λ
0
0.1
0.2
0.5
0.8
Mean Error (%) ↓
54.45
32.08
32.74
34.85
35.57
Table 6: Sensitivity to fusion weight λ on ModelNet40-C with PointNet.
Dataset
Source-only ↓
3D-BBDA ↓
Gain ↑
ModelNet40-C
35.86
32.19
+3.67
ScanObjectNN-C
60.55
59.49
+1.06
ShapeNet-C
35.87
33.11
+2.76
Average
44.09
41.59
+2.49
Table 7: Performance with a single global fusion weight λ=0.1 transferred unchanged across datasets using PointNet.
Figure 3: Qualitative comparison under common corruptions on ModelNet-40C. 3D-BBDA better preserves correct predictions than Source-only and BFTT3D [ 27 ] .
Method
unif
gaus
backg
impul
upsamp
rbf
rbf-inv
den-dec
dens-inc
shear
rot
cut
dist
oclu
lidar
Mean ↓
BFTT3D [ 27 ]
0.584
0.539
0.083
0.524
0.633
0.529
0.541
0.628
0.642
0.492
0.297
0.594
0.521
0.572
0.742
0.528
3D-BBDA (Ours)
0.442
0.421
0.142
0.448
0.486
0.409
0.425
0.575
0.584
0.311
0.049
0.572
0.407
0.370
0.378
0.401
Table 10: Comparison of ECE between BFTT3D and 3D-BBDA on ModelNet-40C.
Noise
unif
gaus
backg
impul
upsamp
rbf
rbf-inv
den-dec
dens-inc
shear
rot
cut
dist
oclu
lidar
Mean ↓
5%
15.36
16.87
93.83
26.10
14.62
24.31
23.41
12.62
10.29
37.21
63.36
13.73
29.21
52.78
52.74
32.43
20%
15.24
17.08
94.28
27.37
14.46
25.29
24.35
12.38
10.21
38.64
64.58
13.36
30.02
52.29
54.00
32.90
50%
14.91
17.36
94.93
29.45
14.05
26.23
24.35
12.05
10.74
40.85
67.69
13.03
31.62
53.27
56.29
33.79
80%
14.34
17.69
95.10
31.99
14.22
28.15
26.10
12.54
10.29
42.65
72.02
13.85
33.46
55.11
58.70
35.08
100%
14.87
17.97
95.02
34.60
15.07
30.51
27.98
13.48
10.91
44.85
73.86
15.69
36.56
57.27
59.56
36.55
Table 11: Quality of the pseudo-labels over proposed 3D-BBDA.
Inference
unif
gaus
backg
impul
upsamp
rbf
rbf-inv
den-dec
den-inc
shear
rot
cut
dist
oclu
lidr
Mean
Standard
3.30
5.37
6.01
6.25
6.32
6.28
6.29
6.28
6.33
6.37
6.34
6.33
6.34
6.33
6.35
6.03
Adapted
8.79
7.95
7.71
7.29
7.16
7.02
6.92
6.89
6.87
6.79
6.74
6.71
6.68
6.67
6.61
7.12
Table 12: Standard vs. adapted inference time (ms) across ModelNet40-C corruptions.
Operation
Frequency
Time
Prototype construction
per target buffer
198.29 ms
Gaussian prior/completion
per target condition
350.65 ms
Shared-subspace alignment
per 128-sample block
669.26 ms
Standard inference
per sample
6.03 ms
Prediction-stage inference
per sample
7.12 ms
Table 13: Runtime decomposition of 3D-BBDA on ModelNet40-C with PointNet. Buffer/block-level adaptation costs are reported.
Figure 11
Dataset
Confidence
Entropy
Coverage (%)
Gain (%) ↑
ModelNet40-C
0.533
0.559
96.17
3.68
ScanObjectNN-C
0.703
0.315
99.11
0.70
ShapeNet-C
0.913
0.057
98.32
2.16
Table 1: Dataset-level diagnostic statistics for the controlled PointNet analysis. Gain is the reduction in classification error relative to Source-only. These statistics are used only to understand the behavior of the adaptation mechanism and do not replace the primary benchmark results.
Diagnostic
r with gain
p
Source confidence
−0.515
0.0004
Predictive entropy
+0.471
0.0014
Class coverage
−0.288
0.0608
Missing classes
+0.315
0.0394
Table 2: Correlation between black-box pseudo-label diagnostics and the adaptation gain across 43 corruption conditions. These results are diagnostic rather than causal.
Dataset
Corruption
Gain (%) ↑
ModelNet40-C
Rotation
+10.86
Impulse
+8.06
Distortion
+6.12
LiDAR
+5.88
Density-inc.
+0.04
ShapeNet-C
RBF-inv
+4.53
Table 3: Examples of large and near-zero adaptation gains. Gains are reported as the reduction in error relative to the corresponding Source-only prediction.
Aspect
BFTT3D
3D-BBDA (Ours)
Problem setting
Backpropagation-free 3D test-time adaptation.
Source-free, logits-only black-box, and backpropagation-free 3D adaptation.
Core intuition
Construct a prototype memory and align target representations with this memory without gradient-based parameter updates.
Retain prototype-based alignment while replacing source-dependent adaptation memory with a memory constructed entirely from unlabeled target data and black-box predictions.
Source data during adaptation
Required for constructing the source-derived adaptation memory.
Frozen source model is accessed only through its final predictions/logits.
Test-time backpropagation
No.
No.
Target representation
Non-parametric target representation.
Frozen PointNN representation independent of the source-model architecture.
Table 4: Detailed methodological comparison between BFTT3D and 3D-BBDA. 3D-BBDA retains the prototype-based shared-subspace alignment principle but removes source-derived adaptation memory. The memory and alignment-system sizes correspond to ShapeNet-C with C=55 and PointNet.
Method
Source data
Source internals
Target BP
Architecture-specific
Evaluation type
3D-BBDA
No
No (logits only)
No
No
Native
PURGE-GATE PG-SF
No
CLS/Q/K
No
Transformer
Native method
PURGE-GATE PG-SP †
Source-derived statistics
Point features
No
Controlled port
PointNet/GDANet
DINE-3D ‡
No
Source probabilities only
Yes
No
Controlled 2D → 3D port
LN-TTA
No
LN/token representations
No
Transformer
PointTransformer only
Table 5: Information-access assumptions of the recent baselines. † denotes our controlled PointNet/GDANet port of PURGE-GATE PG-SP. ‡ denotes our controlled feature-space baselinesport of the 2D black-box adaptation method DINE.
Dataset
Backbone
PG-SP †
DINE-3D ‡
3D-BBDA
ModelNet40-C
PointNet
36.18
46.53
32.08
GDANet
32.61
46.72
29.62
ScanObjectNN-C
PointNet
60.46
68.29
59.48
GDANet
65.71
72.27
65.64
ShapeNet-C
PointNet
36.57
60.90
32.74
GDANet
24.38
54.74
22.85
Table 6: Mean corruption error (%, ↓ ) for the controlled PURGE-GATE and DINE ports.
Recent vision-language models (VLMs) such as CLIP demonstrate impressive cross-modal reasoning, extending beyond images to 3D perception. Yet, these models remain fragile under domain shifts, especially when adapting from synthetic to real-world point clouds. Conventional 3D domain adaptation approaches rely on heavy trainable encoders, yielding strong accuracy but at the cost of efficiency. We introduce CLIPoint3D, the first framework for few-shot unsupervised 3D point cloud domain adaptation built upon CLIP. Our approach projects 3D samples into multiple depth maps and exploits the frozen CLIP backbone, refined through a knowledge-driven prompt tuning scheme that integrates high-level language priors with geometric cues from a lightweight 3D encoder. To adapt task-specific features effectively, we apply parameter-efficient fine-tuning to CLIP's encoders and design an entropy-guided view sampling strategy for selecting confident projections. Furthermore, an optimal transport-based alignment loss and an uncertainty-aware prototype alignment loss collaboratively bridge source-target distribution gaps while maintaining class separability. Extensive experiments on PointDA-10 and GraspNetPC-10 benchmarks show that CLIPoint3D achieves consistent 3-16% accuracy gains over both CLIP-based and conventional encoder-based baselines. Project page: https://sarthakm320.github.io/CLIPoint3D.
Mainak Singha, Sarthak Mehrotra, Paolo Casari +3
University of Trento, Italy · MDSR Labs Adobe, India · IIT Bombay, India +1
The advent of deep neural networks has led to remarkable progress in 3D point cloud recognition, but they remain vulnerable to adversarial attacks. Although various defense methods have been studied, they suffer from a trade-off between robustness and transferability. We propose Adversarial Point Counterattack (APC) to achieve both simultaneously. APC is a lightweight input-level purification module that generates instance-specific counter-perturbations for each point, effectively neutralizing attacks. Leveraging clean-adversarial pairs, APC enforces geometric consistency in data space and semantic consistency in feature space. To improve generalizability across diverse attacks, we adopt a hybrid training strategy using adversarial point clouds from multiple attack types. Since APC operates purely on input point clouds, it directly transfers to unseen models and defends against attacks targeting them without retraining. At inference, a single APC forward pass provides purified point clouds with negligible time and parameter overhead. Extensive experiments on two 3D recognition benchmarks demonstrate that the APC achieves state-of-the-art defense performance. Furthermore, cross-model evaluations validate its superior transferability. The code is available at https://github.com/gyjung975/APC.
Geunyoung Jung, Soohong Kim, Inseok Kong +1
Department of Artificial Intelligence, University of Seoul, South Korea · Department of Geo Informatics, University of Seoul, South Korea
Noisy and corrupted points can substantially degrade point cloud recognition performance, especially under challenging corruption settings. In particular, full fine-tuning of 3D pre-trained models may amplify the influence of outliers and overwrite robustness priors learned during pre-training, while naive parameter-efficient adaptation remains sensitive to corrupted tokens. To address this issue, we propose PSFT, a point-selection fine-tuning framework that improves robustness while remaining parameter-efficient. PSFT first estimates point-wise influence from pre-pooling features and adaptively retains minimally influential points to suppress outliers. Based on the selected subset, a prompt generation branch predicts layer-wise prompt tokens and injects them into a frozen backbone for lightweight downstream adaptation. To further mitigate residual noise after selection, we append a lightweight feature filter with bottleneck MLP transformation and Beta-gated residual blending to refine patch-token representations before prediction. Extensive experiments show that PSFT consistently reduces corruption error on ModelNet-C and ModelNet40-C across all tested 3D pre-trained backbones, while achieving the strongest ScanObjectNN-C results with ULIP-2 and Uni3D-B among the evaluated tuning strategies. Our implementation can be found at https://github.com/CVChMA/PSFT/tree/master.
Da Li, Chang Ma, Dongfu Yin
Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen), Shenzhen, China · Shenzhen University, Shenzhen, China