Hierarchical 3DGS

Hierarchical 3DGS is a dataset released with H3DGS paper. We implement the two public single-chunks scenes (SmallCity, Campus) used for evaluation. To collect the dataset, authors used a bicycle helmet on which they mounted 6 GoPro HERO6 Black cameras (5 for the Campus scene). They collected SmallCity and BigCity captures on a bicycle, riding at around 6–7km/h, while Campus was captured on foot wearing the helmet. Poses were estimated using COLMAP with custom parameters and hierarchical mapper. Additinal per-chunk bundle adjustment was performed. It is recommended to use exposure modeling with this dataset

Web: https://repo-sam.inria.fr/fungraph/hierarchical-3d-gaussians/
Paper: A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets
Authors: Bernhard Kerbl, Andreas Meuleman, Georgios Kopanas, Michael Wimmer, Alexandre Lanvin, George Drettakis
Method PSNR SSIM LPIPS (VGG) Time GPU mem.
H3DGS 25.53
Paper's PSNR: 25.39

Results in the paper were evaluated using different tau (0, 3, 6, 15), where tau=0 is the slowest, but highest quality. We choose tau=6 - consistent with most experiments in the paper, providing a good trade-off between quality and speed.

 0.803
Paper's SSIM: 0.806

Results in the paper were evaluated using different tau (0, 3, 6, 15), where tau=0 is the slowest, but highest quality. We choose tau=6 - consistent with most experiments in the paper, providing a good trade-off between quality and speed.

 0.364 1h 23m 4s 14.94 GB
SmallCity 26.42
Paper's PSNR: 26.29

Results in the paper were evaluated using different tau (0, 3, 6, 15), where tau=0 is the slowest, but highest quality. We choose tau=6 - consistent with most experiments in the paper, providing a good trade-off between quality and speed.

 0.807
Paper's SSIM: 0.81

Results in the paper were evaluated using different tau (0, 3, 6, 15), where tau=0 is the slowest, but highest quality. We choose tau=6 - consistent with most experiments in the paper, providing a good trade-off between quality and speed.

 0.331 1h 16m 1s 15.85 GB
Campus 24.63
Paper's PSNR: 24.5

Results in the paper were evaluated using different tau (0, 3, 6, 15), where tau=0 is the slowest, but highest quality. We choose tau=6 - consistent with most experiments in the paper, providing a good trade-off between quality and speed.

 0.798
Paper's SSIM: 0.801

Results in the paper were evaluated using different tau (0, 3, 6, 15), where tau=0 is the slowest, but highest quality. We choose tau=6 - consistent with most experiments in the paper, providing a good trade-off between quality and speed.

 0.396 1h 30m 7s 14.04 GB

PSNR

Peak Signal to Noise Ratio. The higher the better.

Method SmallCity Campus
H3DGS 26.42
Paper's PSNR: 26.29

Results in the paper were evaluated using different tau (0, 3, 6, 15), where tau=0 is the slowest, but highest quality. We choose tau=6 - consistent with most experiments in the paper, providing a good trade-off between quality and speed.

 24.63
Paper's PSNR: 24.5

Results in the paper were evaluated using different tau (0, 3, 6, 15), where tau=0 is the slowest, but highest quality. We choose tau=6 - consistent with most experiments in the paper, providing a good trade-off between quality and speed.

SSIM

Structural Similarity Index. The higher the better. The implementation matches JAX's SSIM and torchmetrics's SSIM (with default parameters).

Method SmallCity Campus
H3DGS 0.807
Paper's SSIM: 0.81

Results in the paper were evaluated using different tau (0, 3, 6, 15), where tau=0 is the slowest, but highest quality. We choose tau=6 - consistent with most experiments in the paper, providing a good trade-off between quality and speed.

 0.798
Paper's SSIM: 0.801

Results in the paper were evaluated using different tau (0, 3, 6, 15), where tau=0 is the slowest, but highest quality. We choose tau=6 - consistent with most experiments in the paper, providing a good trade-off between quality and speed.

LPIPS (VGG)

Learned Perceptual Image Patch Similarity. The lower the better. The implementation uses VGG backbone and matches lpips pip package with checkpoint version 0.1

Method SmallCity Campus
H3DGS 0.331 0.396