Test Accuracy: 86.67%




The tall back dominates the silhouette. The short seat is easy to miss, so the overall shape resembles a narrow floor lamp.
The vase has a wide base and a narrow middle. The flared top could resemble a small lampshade above a stem.
The rounded base runs into the shade with little visible separation. The outline resembles a single bulbous vessel.
Test Accuracy: 84.44%


The backrest is recognizable, but the model breaks up the chair’s arm and side into seat and leg labels. It also treats the separate piece in front as if it were another seat with legs.


The matching footrest is separate from the armchair, but the model labels it as if it were part of another chair. On the armchair itself, the backrest label spills into the seat.


The cutout backrest and legs are easy to pick out in both views. The prediction gets fuzzy where the seat meets the legs, with the leg label extending onto the seat.


The stool’s backrest, seat, and long legs are recognizable. The seat label runs down the tops of the legs where they join the seat.


The prediction preserves the major parts. The main slip is where the armrest reaches the backrest and some of it picks up the backrest label.
I rotated each test cloud about its centroid around the Z axis and evaluated the original Q1 and Q2 checkpoints with the same labels.
| Angle | Classification | Segmentation |
|---|---|---|
| 0° (clean) | 86.67% | 84.44% |
| 15° | 83.42% | 81.96% |
| 45° | 65.48% | 65.32% |
| 90° | 46.07% | 46.68% |
| 180° | 43.55% | 31.78% |
The larger rotations create an out-of-distribution test: the shapes stay the same, but their XYZ coordinates no longer follow the orientations the models saw during training. PointNet’s max pooling handles point order, while its encoder can still learn orientation cues from XYZ. For example, a tilted chair can move leg points into positions the model associates with the back or seat. By 90°, both accuracies fell below 47%.


I added independent zero-mean Gaussian noise to each XYZ coordinate. The table gives the standard deviation in the input coordinate units.
| Standard deviation (σ) | Classification | Segmentation |
|---|---|---|
| 0 (clean) | 86.67% | 84.44% |
| 0.005 | 86.57% | 84.37% |
| 0.015 | 86.36% | 84.04% |
| 0.025 | 85.94% | 83.45% |
| 0.05 | 85.94% | 81.03% |
Both models were close to their clean accuracy at σ = 0.005. At σ = 0.05, segmentation lost 3.41 percentage points and classification lost 0.73 points. Jitter makes part boundaries less distinct while leaving the overall object shape recognizable.


EdgeConv is a message-passing layer for point clouds. For each point, I built a fixed graph using its eight nearest neighbors in XYZ. A shared MLP turns each neighbor’s offset and the center point’s coordinates into a message, and a max over those messages gives the point a feature that depends on its neighborhood. I used one EdgeConv layer in place of PointNet’s point encoder. The classifier pools the features over the whole cloud, and the segmentation head combines each point’s feature with the pooled cloud feature before labeling it. Wang et al., Dynamic Graph CNN for Learning on Point Clouds (2019).
| Model | Classification | Segmentation |
|---|---|---|
| Original Q1/Q2 (10,000 points) | 86.67% | 84.44% |
| Matched PointNet (1,024 points) | 93.70% | 83.76% |
| EdgeConv (1,024 points) | 93.28% | 85.33% |
The matched runs shared the same point samples, training and validation split, and 10-epoch budget. The figures evaluate all three checkpoints on the same 1,024 points per cloud.

