Presented: Dijing Zhang
source voxel
target voxel
source point cloud
target point cloud
Source Mesh
Target Mesh
Example1 - RGB
Example1 - GT
Example1 - Pred
Example2 - RGB
Example2 - GT
Example2 - Pred
Example3 - RGB
Example3 - GT
Example3 - Pred
Example1 - RGB
Example1 - GT
Example1 - Pred
Example2 - RGB
Example2 - GT
Example2 - Pred
Example3 - RGB
Example3 - GT
Example3 - Pred
Example1 - RGB
Example1 - GT
Example1 - Pred
Example2 - RGB
Example2 - GT
Example2 - Pred
Example3 - RGB
Example3 - GT
Example3 - Pred
F1 @ 0.05
Voxel: 84.2379
Mesh: 71.2455
Point: 57.9918
As we can see here, the voxel has the greatest F1 @ 0.05 because I design a much more complex model for voxel prediction while point-model and mesh-model are much simpler, almost composed of linear layers.
Besides, the metric for point is lower than the others. It is becuase of the discrete format of point cloud while voxel and mesh has instrinic connection
w_smooth: By changing the hyperparameters, we change the weight for mesh smoothness, which can help to get a more smooth mesh result if we increase the value of w_smooth. And it will be really helpful to increase the metric. But if set too large weight, we will get a abstract shape, like every chair will show the same shape.
n_point: By changing the hyperparameters, we change the sampled point for point cloud. Typically, we need at least 1024 points to show the shape and with the increase of n_point, we can have a much more accurate presentation but less accurate because we need to predict more points. The F1-score will decrease as n_point increases.
batch_size: Batch_size plays a great role in convergence of model. Default value is too small and at least 32 can help model to converge and not cause overfitting.
arch: the default uses resnet18. We can change it to resnet50 or even larger one, like resnet101 to enhance the feature extraction. It will greatly increase the performance.
1. Show voxel with probability color
The higher probability of each cell will appear as darker color. And as we can see, the main part of the chair tends to have darker color and the trivial part tends to not.
2. Transformer of meshes!
Insight into how model gradually predict a chair!