# Soundscape-to-image generation on SonicUrban 237K

Source: [Soundscape-to-image generation on SonicUrban 237K](<https://www.sota2.com/research/sota/soundscape-to-image-generation-on-sonicurban-237k>)

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

Data updated: 2026-03-04T07:33:56.975Z

Evaluation of models performing soundscape-to-image generation using the SonicUrban 237K dataset, assessed using metrics like FID, AIS, IIS, and PSS scores.

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 | Soundscape-to-image generation |
| Dataset (including any stated split) | SonicUrban 237K |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

- [FID](<https://www.sota2.com/research/sota/soundscape-to-image-generation-on-sonicurban-237k.md?metric=FID>): Lower is better; unit: SCALAR.

- [AIS](<https://www.sota2.com/research/sota/soundscape-to-image-generation-on-sonicurban-237k.md?metric=AIS>): Higher is better; unit: SCALAR.

- [IIS](<https://www.sota2.com/research/sota/soundscape-to-image-generation-on-sonicurban-237k.md?metric=IIS>): Higher is better; unit: SCALAR.

- [PSS (Element)](<https://www.sota2.com/research/sota/soundscape-to-image-generation-on-sonicurban-237k.md?metric=PSS%20(Element)>): Higher is better; unit: SCALAR.

- [PSS (Scene)](<https://www.sota2.com/research/sota/soundscape-to-image-generation-on-sonicurban-237k.md?metric=PSS%20(Scene)>): Higher is better; unit: SCALAR.

- [PSS (Perception)](<https://www.sota2.com/research/sota/soundscape-to-image-generation-on-sonicurban-237k.md?metric=PSS%20(Perception)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| SounDiT | 11.553 | Not recorded | 68fa789b1e209131cea79499 |
| PixArt + MHCA | 41.456 | Not recorded | 68fa789b1e209131cea79499 |
| Sound2Scene | 49.681 | Not recorded | 68fa789b1e209131cea79499 |
| GlueGen | 64.434 | Not recorded | 68fa789b1e209131cea79499 |
| CoDi | 83.904 | Not recorded | 68fa789b1e209131cea79499 |
| AudioToken | 95.21 | Not recorded | 68fa789b1e209131cea79499 |
| AudioToken | 127.337 | Not recorded | 68fa789b1e209131cea79499 |
| AudioToken | 165.014 | Not recorded | 68fa789b1e209131cea79499 |

### SounDiT

FID: 11.553. Result ID: 69a7e01e6dbb7075b94c65d7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789b1e209131cea79499.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa789b1e209131cea79499.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PixArt + MHCA

FID: 41.456. Result ID: 69a7e01e6dbb7075b94c65d6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789b1e209131cea79499.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71a41e209131cea5240a.md>)

[Implementation](<https://pixart-alpha.github.io/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Sound2Scene

FID: 49.681. Result ID: 69a7e01e6dbb7075b94c65d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789b1e209131cea79499.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ef21e209131cea4317e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GlueGen

FID: 64.434. Result ID: 69a7e01e6dbb7075b94c65d5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789b1e209131cea79499.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71131e209131cea4f1bb.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CoDi

FID: 83.904. Result ID: 69a7e01e6dbb7075b94c65d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789b1e209131cea79499.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f711e209131cea459cf.md>)

[Implementation](<https://codi-gen.github.io/>)

Recorded evaluation configuration: {"Pre-trained":"true"}. This record does not assert independent reproduction.

### AudioToken

FID: 95.21. Result ID: 69a7e01e6dbb7075b94c65d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789b1e209131cea79499.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f651e209131cea454d3.md>)

Recorded evaluation configuration: {"Backbone/Base Model":"SD1"}. This record does not assert independent reproduction.

### AudioToken

FID: 127.337. Result ID: 69a7e01e6dbb7075b94c65d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789b1e209131cea79499.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f651e209131cea454d3.md>)

Recorded evaluation configuration: {"Pre-trained":"true"}. This record does not assert independent reproduction.

### AudioToken

FID: 165.014. Result ID: 69a7e01e6dbb7075b94c65d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa789b1e209131cea79499.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f651e209131cea454d3.md>)

Recorded evaluation configuration: {"Backbone/Base Model":"SD2"}. This record does not assert independent reproduction.

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