# 3D Point Cloud Classification on ScanObjectNN-C 1.0 (test)

Source: [3D Point Cloud Classification on ScanObjectNN-C 1.0 (test)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-12T07:28:16.803Z

Evaluation of 3D Point Cloud Classification performance on the ScanObjectNN-C 1.0 test split, reporting accuracy across various corruption types (e.g., uniform noise, Gaussian noise, occlusion, rotation).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | 3D Point Cloud Classification |
| Dataset (including any stated split) | ScanObjectNN-C 1.0 (test) |
| Metric | Accuracy (Uniform Noise) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy (Uniform Noise)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Uniform%20Noise)>): Higher is better; unit: PERCENT.

- [Accuracy (Gaussian Noise)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Gaussian%20Noise)>): Higher is better; unit: PERCENT.

- [Accuracy (Background)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Background)>): Higher is better; unit: PERCENT.

- [Accuracy (Impulse Noise)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Impulse%20Noise)>): Higher is better; unit: PERCENT.

- [Accuracy (Upsampling)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Upsampling)>): Higher is better; unit: PERCENT.

- [Accuracy (RBF Distortion)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(RBF%20Distortion)>): Higher is better; unit: PERCENT.

- [Accuracy (Inverse RBF Distortion)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Inverse%20RBF%20Distortion)>): Higher is better; unit: PERCENT.

- [Accuracy (Density Decrease)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Density%20Decrease)>): Higher is better; unit: PERCENT.

- [Accuracy (Density Increase)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Density%20Increase)>): Higher is better; unit: PERCENT.

- [Accuracy (Shear)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Shear)>): Higher is better; unit: PERCENT.

- [Accuracy (Rotation)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Rotation)>): Higher is better; unit: PERCENT.

- [Accuracy (Cutout/Occlusion)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Cutout%2FOcclusion)>): Higher is better; unit: PERCENT.

- [Accuracy (Distortion)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Distortion)>): Higher is better; unit: PERCENT.

- [Accuracy (Occlusion)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(Occlusion)>): Higher is better; unit: PERCENT.

- [Accuracy (LiDAR Noise)](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Accuracy%20(LiDAR%20Noise)>): Higher is better; unit: PERCENT.

- [Mean Accuracy](<https://www.sota2.com/research/sota/3d-point-cloud-classification-on-scanobjectnn-c-1-0-test.md?metric=Mean%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Uniform Noise) | Result date | Report paper |
| --- | --- | --- | --- |
| SVWA | 44.62 | Not recorded | 6a2b92bad33dfb23e783b176 |
| MAMVI | 43.06 | Not recorded | 6a2b92bad33dfb23e783b176 |
| SAR | 41.65 | Not recorded | 6a2b92bad33dfb23e783b176 |
| PG-SP | 41.48 | Not recorded | 6a2b92bad33dfb23e783b176 |
| PG-SF | 40.96 | Not recorded | 6a2b92bad33dfb23e783b176 |
| PL | 39.76 | Not recorded | 6a2b92bad33dfb23e783b176 |
| TENT | 39.24 | Not recorded | 6a2b92bad33dfb23e783b176 |
| T3A | 37.5 | Not recorded | 6a2b92bad33dfb23e783b176 |
| DUA | 30.5 | Not recorded | 6a2b92bad33dfb23e783b176 |
| TTT-Rot | 30.2 | Not recorded | 6a2b92bad33dfb23e783b176 |
| MATE | 27.5 | Not recorded | 6a2b92bad33dfb23e783b176 |
| SMART-PC | 27.5 | Not recorded | 6a2b92bad33dfb23e783b176 |
| SHOT | 25.82 | Not recorded | 6a2b92bad33dfb23e783b176 |
| Source Only | 21.69 | Not recorded | 6a2b92bad33dfb23e783b176 |
| BFTT3D | 16.35 | Not recorded | 6a2b92bad33dfb23e783b176 |
| LAME | 14.46 | Not recorded | 6a2b92bad33dfb23e783b176 |

### SVWA

Accuracy (Uniform Noise): 44.62. Result ID: 6a2bb504fbc373592c29c039.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76731e209131cea6d161.md>)

Recorded evaluation configuration: {"Method Category":"Source-Free Methods"}. This record does not assert independent reproduction.

### MAMVI

Accuracy (Uniform Noise): 43.06. Result ID: 6a2bb504fbc373592c29c03a.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

Recorded evaluation configuration: {"Method Category":"Source-Free Methods"}. This record does not assert independent reproduction.

### SAR

Accuracy (Uniform Noise): 41.65. Result ID: 6a2bb504fbc373592c29c037.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e961e209131cea40e77.md>)

Recorded evaluation configuration: {"Method Category":"Source-Free Methods"}. This record does not assert independent reproduction.

### PG-SP

Accuracy (Uniform Noise): 41.48. Result ID: 6a2bb504fbc373592c29c030.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b411e209131cea87531.md>)

Recorded evaluation configuration: {"Method Category":"Source-Dependent Methods"}. This record does not assert independent reproduction.

### PG-SF

Accuracy (Uniform Noise): 40.96. Result ID: 6a2bb504fbc373592c29c038.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b411e209131cea87531.md>)

Recorded evaluation configuration: {"Method Category":"Source-Free Methods"}. This record does not assert independent reproduction.

### PL

Accuracy (Uniform Noise): 39.76. Result ID: 6a2bb504fbc373592c29c031.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

Recorded evaluation configuration: {"Method Category":"Source-Free Methods"}. This record does not assert independent reproduction.

### TENT

Accuracy (Uniform Noise): 39.24. Result ID: 6a2bb504fbc373592c29c032.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69941e209131cea22d2b.md>)

Recorded evaluation configuration: {"Method Category":"Source-Free Methods"}. This record does not assert independent reproduction.

### T3A

Accuracy (Uniform Noise): 37.5. Result ID: 6a2bb504fbc373592c29c034.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

Recorded evaluation configuration: {"Method Category":"Source-Free Methods"}. This record does not assert independent reproduction.

### DUA

Accuracy (Uniform Noise): 30.5. Result ID: 6a2bb504fbc373592c29c036.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2a1e209131cea3277e.md>)

[Implementation](<https://github.com/jmiemirza/DUA>)

Recorded evaluation configuration: {"Method Category":"Source-Free Methods"}. This record does not assert independent reproduction.

### TTT-Rot

Accuracy (Uniform Noise): 30.2. Result ID: 6a2bb504fbc373592c29c02c.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d01e209131cea189f7.md>)

[Implementation](<https://test-time-training.github.io/>)

Recorded evaluation configuration: {"Method Category":"TTT Methods"}. This record does not assert independent reproduction.

### MATE

Accuracy (Uniform Noise): 27.5. Result ID: 6a2bb504fbc373592c29c02d.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ecf1e209131cea4250a.md>)

Recorded evaluation configuration: {"Method Category":"TTT Methods"}. This record does not assert independent reproduction.

### SMART-PC

Accuracy (Uniform Noise): 27.5. Result ID: 6a2bb504fbc373592c29c02e.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c11e209131cea7a4f0.md>)

Recorded evaluation configuration: {"Method Category":"TTT Methods"}. This record does not assert independent reproduction.

### SHOT

Accuracy (Uniform Noise): 25.82. Result ID: 6a2bb504fbc373592c29c033.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a0e1e209131cea25d69.md>)

[Implementation](<https://github.com/tim-learn/SHOT>)

Recorded evaluation configuration: {"Method Category":"Source-Free Methods"}. This record does not assert independent reproduction.

### Source Only

Accuracy (Uniform Noise): 21.69. Result ID: 6a2bb504fbc373592c29c02b.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

Recorded evaluation configuration: {"Method Category":"Baseline"}. This record does not assert independent reproduction.

### BFTT3D

Accuracy (Uniform Noise): 16.35. Result ID: 6a2bb504fbc373592c29c02f.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72f81e209131cea59a6b.md>)

Recorded evaluation configuration: {"Method Category":"Source-Dependent Methods"}. This record does not assert independent reproduction.

### LAME

Accuracy (Uniform Noise): 14.46. Result ID: 6a2bb504fbc373592c29c035.

[Reporting paper](<https://www.sota2.com/research/paper/6a2b92bad33dfb23e783b176.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c341e209131cea32ca1.md>)

[Implementation](<https://github.com/fiveai/LAME>)

Recorded evaluation configuration: {"Method Category":"Source-Free Methods"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
