# Lip Synchronization on HDTF

Source: [Lip Synchronization on HDTF](<https://www.sota2.com/research/sota/lip-synchronization-on-hdtf>)

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

Data updated: 2026-03-11T07:09:25.064Z

Evaluation of Lip Synchronization performance on the HDTF dataset, utilizing metrics such as FID, FVD, CSIM, NIQE, BRISQUE, HyperIQA, LMD, and LSE-C.

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 | Lip Synchronization |
| Dataset (including any stated split) | HDTF |
| 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/lip-synchronization-on-hdtf.md?metric=FID>): Lower is better; unit: SCALAR.

- [FVD](<https://www.sota2.com/research/sota/lip-synchronization-on-hdtf.md?metric=FVD>): Lower is better; unit: SCALAR.

- [CSIM](<https://www.sota2.com/research/sota/lip-synchronization-on-hdtf.md?metric=CSIM>): Higher is better; unit: PERCENT.

- [NIQE](<https://www.sota2.com/research/sota/lip-synchronization-on-hdtf.md?metric=NIQE>): Lower is better; unit: SCALAR.

- [BRISQUE](<https://www.sota2.com/research/sota/lip-synchronization-on-hdtf.md?metric=BRISQUE>): Lower is better; unit: SCALAR.

- [HyperIQA](<https://www.sota2.com/research/sota/lip-synchronization-on-hdtf.md?metric=HyperIQA>): Higher is better; unit: SCALAR.

- [LMD](<https://www.sota2.com/research/sota/lip-synchronization-on-hdtf.md?metric=LMD>): Lower is better; unit: SCALAR.

- [LSE-C](<https://www.sota2.com/research/sota/lip-synchronization-on-hdtf.md?metric=LSE-C>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| OmniEdit | 7.623 | Not recorded | 69b0f6f82d603e6de3e45c98 |
| Omnisync | 7.855 | Not recorded | 69b0f6f82d603e6de3e45c98 |
| OmniEdit | 7.952 | Not recorded | 69b0f6f82d603e6de3e45c98 |
| LatentSync | 8.518 | Not recorded | 69b0f6f82d603e6de3e45c98 |
| MuseTalk | 8.759 | Not recorded | 69b0f6f82d603e6de3e45c98 |
| IP-LAP | 9.512 | Not recorded | 69b0f6f82d603e6de3e45c98 |
| Diff2Lip | 12.079 | Not recorded | 69b0f6f82d603e6de3e45c98 |
| Wav2Lip | 14.912 | Not recorded | 69b0f6f82d603e6de3e45c98 |

### OmniEdit

FID: 7.623. Result ID: 69b1150a6dbb7075b95afc34.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c98.md>)

Recorded evaluation configuration: {"Model size":"17B","Backbone":"Humo"}. This record does not assert independent reproduction.

### Omnisync

FID: 7.855. Result ID: 69b1150a6dbb7075b95afc32.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b5f1e209131cea87fd2.md>)

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

### OmniEdit

FID: 7.952. Result ID: 69b1150a6dbb7075b95afc33.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c98.md>)

Recorded evaluation configuration: {"Model size":"1.7B","Backbone":"Humo"}. This record does not assert independent reproduction.

### LatentSync

FID: 8.518. Result ID: 69b1150a6dbb7075b95afc31.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa776a1e209131cea7323a.md>)

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

### MuseTalk

FID: 8.759. Result ID: 69b1150a6dbb7075b95afc30.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77a01e209131cea74751.md>)

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

### IP-LAP

FID: 9.512. Result ID: 69b1150a6dbb7075b95afc2e.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f561e209131cea451ed.md>)

[Implementation](<https://github.com/Weizhi-Zhong/IP_LAP>)

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

### Diff2Lip

FID: 12.079. Result ID: 69b1150a6dbb7075b95afc2f.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70571e209131cea4a643.md>)

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

### Wav2Lip

FID: 14.912. Result ID: 69b1150a6dbb7075b95afc2d.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f6f82d603e6de3e45c98.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68361e209131cea1ad36.md>)

[Implementation](<https://www.sota2.com/github.com/Rudrabha/Wav2Lip>)

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

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