# Dynamic Scene Reconstruction on D-NeRF Synthetic Bouncing Balls 800x800 resolution (test)

Source: [Dynamic Scene Reconstruction on D-NeRF Synthetic Bouncing Balls 800x800 resolution (test)](<https://www.sota2.com/research/sota/dynamic-scene-reconstruction-on-d-nerf-synthetic-bouncing-balls-800x800-resolution-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:55:53.765Z

Evaluation of Dynamic Scene Reconstruction performance on the test split of the D-NeRF Synthetic Bouncing Balls dataset (800x800 resolution), measured using image quality metrics PSNR, SSIM, and LPIPS.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Dynamic Scene Reconstruction |
| Dataset (including any stated split) | D-NeRF Synthetic Bouncing Balls 800x800 resolution (test) |
| Metric | PSNR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [PSNR](<https://www.sota2.com/research/sota/dynamic-scene-reconstruction-on-d-nerf-synthetic-bouncing-balls-800x800-resolution-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/dynamic-scene-reconstruction-on-d-nerf-synthetic-bouncing-balls-800x800-resolution-test.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [LPIPS](<https://www.sota2.com/research/sota/dynamic-scene-reconstruction-on-d-nerf-synthetic-bouncing-balls-800x800-resolution-test.md?metric=LPIPS>): Lower is better; unit: SCALAR.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| Deformable 3D Gaussians | 41.01 | Not recorded | 68fa713a1e209131cea4fe7b |
| TiNeuVox | 40.23 | Not recorded | 68fa713a1e209131cea4fe7b |
| K-Planes | 40.05 | Not recorded | 68fa713a1e209131cea4fe7b |
| D-NeRF | 38.17 | Not recorded | 68fa713a1e209131cea4fe7b |
| Tensor4D | 24.47 | Not recorded | 68fa713a1e209131cea4fe7b |
| 3D-GS | 23.2 | Not recorded | 68fa713a1e209131cea4fe7b |

### Deformable 3D Gaussians

PSNR: 41.01. Result ID: 6991bc923a6c3148490a3e40.

[Reporting paper](<https://www.sota2.com/research/paper/68fa713a1e209131cea4fe7b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa713a1e209131cea4fe7b.md>)

[Implementation](<https://github.com/ingra14m/Deformable-3D-Gaussians>)

Recorded evaluation configuration: {"Resolution":"800x800"}. This record does not assert independent reproduction.

### TiNeuVox

PSNR: 40.23. Result ID: 6991bc923a6c3148490a3e3d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa713a1e209131cea4fe7b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d851e209131cea3a5db.md>)

Recorded evaluation configuration: {"Resolution":"800x800"}. This record does not assert independent reproduction.

### K-Planes

PSNR: 40.05. Result ID: 6991bc923a6c3148490a3e3f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa713a1e209131cea4fe7b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42d16.md>)

[Implementation](<https://github.com/sarafridov/K-Planes>)

Recorded evaluation configuration: {"Resolution":"800x800"}. This record does not assert independent reproduction.

### D-NeRF

PSNR: 38.17. Result ID: 6991bc923a6c3148490a3e3c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa713a1e209131cea4fe7b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68da1e209131cea1eaf8.md>)

Recorded evaluation configuration: {"Resolution":"800x800"}. This record does not assert independent reproduction.

### Tensor4D

PSNR: 24.47. Result ID: 6991bc923a6c3148490a3e3e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa713a1e209131cea4fe7b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f061e209131cea43570.md>)

Recorded evaluation configuration: {"Resolution":"800x800"}. This record does not assert independent reproduction.

### 3D-GS

PSNR: 23.2. Result ID: 6991bc923a6c3148490a3e3b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa713a1e209131cea4fe7b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70461e209131cea4a191.md>)

[Implementation](<https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/>)

Recorded evaluation configuration: {"Resolution":"800x800"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
