Hyperparameter Analysis:
Modify the w_smooth to see the difference. The results are really spikey when w_smooth == 0.1, so I change the w_smooth to 5 to see how the results would be changed correspondingly.
As we can see below, smoother parameters lead to smoother results. But it also makes all the results look really similar. Difference image inputs can generate almost the same results. I think it is because the w_smooth is to control how much each vertex deviates from the neighbors, making the results really similar, especially when the number of training step (around 1500) is not that large.
w_smooth == 0.1
w_smooth == 0.1
w_smooth == 0.1
w_smooth == 5
w_smooth == 5
w_smooth == 5
Add Gaussian Noise
Gaussian noise has been added to the loaded image features. Set the mean = 0.0 and std = [0.1, 0.5, 1.0, 2.0, 5.0]
std = [0.1, 0.5] will not significantly influence the results. std = 1.0 or higher will cause visable influence on the results.
mean = 0.0, std = 0.1
mean = 0.0, std = 0.5
mean = 0.0, std = 1.0
mean = 0.0, std = 2.0
mean = 0.0, std = 5.0
mean = 0.0, std = 0.1
mean = 0.0, std = 0.5
mean = 0.0, std = 1.0
mean = 0.0, std = 2.0
mean = 0.0, std = 5.0
At first the model is without Position Encoding. Even trained for over 3k steps, the results look like just noise. The current results are based PE and mlp.