| Rank | Model |
PSNR | SSIM | LPIPS | Average PSNR | Size (MB) |
Paper | Code | Year |
| 1 |
Deformable Beta Splatting |
34.66 | 0.973 | 0.028 | – | – |
Deformable Beta Splatting
|
RongLiu-Leo/beta-splatting |
2025 |
| 2 |
Self-Organizing Gaussians |
33.7 | 0.969 | 0.031 | – | 4.1 |
Compact 3D Scene Representation via Self-Organizing Gaussian Grids
|
facebookresearch/uco3d · fraunhoferhhi/Self-Organizing-Gaussians |
2023 |
| 3 |
I-NGP |
33.18 | – | – | – | – |
K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
|
MaximeVandegar/Papers-in-100-Lines-of-Code · sarafridov/k-planes |
2023 |
| 4 |
TensoRF |
33.14 | 0.963 | – | – | – |
K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
|
MaximeVandegar/Papers-in-100-Lines-of-Code · sarafridov/k-planes |
2023 |
| 5 |
K-Planes (hybrid) |
32.36 | 0.967 | – | – | – |
K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
|
MaximeVandegar/Papers-in-100-Lines-of-Code · sarafridov/k-planes |
2023 |
| 6 |
K-Planes (explicit) |
32.21 | 0.964 | – | – | – |
K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
|
MaximeVandegar/Papers-in-100-Lines-of-Code · sarafridov/k-planes |
2023 |
| 7 |
Plenoxels |
31.71 | 0.958 | – | – | – |
K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
|
MaximeVandegar/Papers-in-100-Lines-of-Code · sarafridov/k-planes |
2023 |
| 8 |
JAXNeRF |
31.65 | 0.952 | 0.051 | – | – |
MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
|
google-research/jax3d |
2022 |
| 9 |
NeRF |
31 | 0.947 | 0.081 | – | – |
MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
|
google-research/jax3d |
2022 |
| 10 |
MobileNeRF |
30.9 | 0.947 | 0.062 | – | – |
MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
|
google-research/jax3d |
2022 |
| 11 |
SNeRG |
30.38 | 0.95 | 0.05 | – | – |
MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures
|
google-research/jax3d |
2022 |
| 12 |
PVD_Hash2NeRF |
– | – | – | 30.76 | – |
One is All: Bridging the Gap Between Neural Radiance Fields Architectures with Progressive Volume Distillation
|
megvii-research/AAAI2023-PVD |
2022 |