# 3D Scene Compression and Object Isolation on Temple 302 views, 3 masks

Source: [3D Scene Compression and Object Isolation on Temple 302 views, 3 masks](<https://www.sota2.com/research/sota/3d-scene-compression-and-object-isolation-on-temple-302-views-3-masks>)

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

Data updated: 2026-02-26T05:39:41.138Z

Evaluation of methods for 3D scene compression and object isolation using the Temple 302 views, 3 masks dataset, measured by metrics related to model size, compression ratio, and processing time.

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 | 3D Scene Compression and Object Isolation |
| Dataset (including any stated split) | Temple 302 views, 3 masks |
| Metric | Compression Rate (%) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Compression Rate (%)](<https://www.sota2.com/research/sota/3d-scene-compression-and-object-isolation-on-temple-302-views-3-masks.md?metric=Compression%20Rate%20(%25)>): Higher is better; unit: PERCENT.

- [Number of Gaussians](<https://www.sota2.com/research/sota/3d-scene-compression-and-object-isolation-on-temple-302-views-3-masks.md?metric=Number%20of%20Gaussians>): Higher is better; unit: SCALAR.

- [Size (MB)](<https://www.sota2.com/research/sota/3d-scene-compression-and-object-isolation-on-temple-302-views-3-masks.md?metric=Size%20(MB)>): Lower is better; unit: SIZE.

- [Processing Time](<https://www.sota2.com/research/sota/3d-scene-compression-and-object-isolation-on-temple-302-views-3-masks.md?metric=Processing%20Time>): Lower is better; unit: TIME.

## Recorded results

| Method | Compression Rate (%) | Result date | Report paper |
| --- | --- | --- | --- |
| Clean-GS | 62.4 | Not recorded | 695c96f453fdd5c36174357f |
| Basic | 60.4 | Not recorded | 695c96f453fdd5c36174357f |
| Original | 0 | Not recorded | 695c96f453fdd5c36174357f |

### Clean-GS

Compression Rate (%): 62.4. Result ID: 6997f6665698665ec44fb7aa.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f453fdd5c36174357f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695c96f453fdd5c36174357f.md>)

Recorded evaluation configuration: {"Components":"Full method with neighbor-based outlier removal","Stages":"1-3"}. This record does not assert independent reproduction.

### Basic

Compression Rate (%): 60.4. Result ID: 6997f6665698665ec44fb7a9.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f453fdd5c36174357f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695c96f453fdd5c36174357f.md>)

Recorded evaluation configuration: {"Components":"Whitelist + Color validation","Stages":"1-2"}. This record does not assert independent reproduction.

### Original

Compression Rate (%): 0. Result ID: 6997f6665698665ec44fb7a8.

[Reporting paper](<https://www.sota2.com/research/paper/695c96f453fdd5c36174357f.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: {"Description":"Unmodified 3DGS model"}. This record does not assert independent reproduction.

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