Q1 · Classification
Test accuracy 97.5866%
Random test point clouds
Misclassified point clouds
The tall, narrow chair back may look like a floor lamp.
The wide rim may look like a lampshade.
The lamp’s large, angular top may look like a decorative vase.
Q2 · Segmentation
Test accuracy 89.5962%
| Object | Ground truth | Prediction | Point accuracy |
|---|---|---|---|
| 0 | ![]() |
![]() |
94.0700% |
| 1 | ![]() |
![]() |
98.4100% |
| 2 | ![]() |
![]() |
87.3400% |
| Failure 351 | ![]() |
![]() |
42.0700% |
| Failure 26 | ![]() |
![]() |
46.1200% |
The model separated the seats, backs, and supports well on chairs 0 and 1. On chair 2, most mistakes appear near the seat and armrest boundaries. For chair 351, the model labeled much of the lower shell as legs. For chair 26, it labeled the headrest as part of the back and much of the armrest as seat.
Q3 · Robustness
Experiment 1 · Rotation
We rotate each test point cloud by 30°, 60°, and 90° around the vertical Y axis and evaluate the trained Q1 and Q2 models.
Experiment 2 · Point count
We evaluate the same models on 2,500, 1,000, and 250 points per object. We sample without replacement using a fixed random seed. Each smaller set is a subset of the larger sets, and segmentation is scored on the retained points.
| Condition | Classification accuracy | Segmentation accuracy |
|---|---|---|
| Q1 / Q2 baseline (10,000 points) | 97.5866% | 89.5962% |
| 30° rotation | 91.3956% | 77.0828% |
| 60° rotation | 76.7051% | 56.3565% |
| 90° rotation | 62.6443% | 47.5078% |
| 2,500 points | 97.6915% | 89.4756% |
| 1,000 points | 97.0619% | 89.1066% |
| 250 points | 96.5373% | 85.2947% |
Rotation results
Accuracy fell as the angle increased. At 90°, classification dropped by 34.94 percentage points and segmentation dropped by 42.09. At 60°, the classifier mistook chair 487 for a vase. At 90°, the segmentation model mislabeled most of chair 0's back.
Point-count results
Both tasks stayed close to baseline at 1,000 points. At 250 points, classification dropped by 1.05 percentage points and segmentation dropped by 4.30. The three illustrated objects kept their predicted classes, but chair 1's segmentation accuracy fell from 98.4% to 91.6%.
Q4 · Locality (bonus)
We use a compact DGCNN with two EdgeConv layers and 16 neighbors per point. The first layer finds neighbors in XYZ space. The second rebuilds the graph in the learned feature space. Each layer uses a shared MLP and max pooling over the neighbors. Classification uses a global descriptor, and segmentation combines that descriptor with each point's local features.
We select each DGCNN checkpoint by validation accuracy and compare it with the original PointNet on identical sampled test points.
| Model | Classification accuracy | Segmentation accuracy |
|---|---|---|
| PointNet (Q1/Q2, 10,000 points) | 97.5866% | 89.5962% |
| PointNet (1,024 points) | 97.1668% | 88.9492% |
| DGCNN (1,024 points) | 96.4323% | 90.3262% |
On the same 1,024 points, DGCNN scored 0.73 percentage points lower on classification and 1.38 points higher on segmentation. Both models correctly classified all three objects shown.
On chair 26, DGCNN improved point accuracy from 51.2% to 59.6%. Both models still mislabeled its headrest as part of the back.









