Vaibhav Parekh | Fall 2025
Opacities: 0.005
Scales: 0.001
Colors: 0.002
Means: 0.001
No. of iterations: 1000
PSNR: 29.628
SSIM: 0.934
Opacities: 0.005
Scales: 0.001
Colors: 0.002
Means: 0.001
Quats: 0.002
No. of iterations: 1000
PSNR: 21.360
SSIM: 0.648
Opacities: 0.005
Scales: 0.001
Colors: 0.002
Means: 0.001
Quats: 0.002
No. of iterations: 1000
PSNR: 24.673
SSIM: 0.693
Explanation of improvements: For improvement over the baseline, I used anisotropic Gaussians while keeping hyperparameters remained unchanged. Although the improved version slightly increased training time as compared to baseline, it produced cleaner results.
Implementation:
In this implementation, I first encode the image, find latent targets, and then decode the latents into the image.
Mean squared error is computed between input and target images.
Analysis:
The training is heavier in terms of memory and time, and yields only marginal improvements in results.