# Generative Video Enhancement on Novel Trajectory and Object Insertion Simulation (test)

Source: [Generative Video Enhancement on Novel Trajectory and Object Insertion Simulation (test)](<https://www.sota2.com/research/sota/generative-video-enhancement-on-novel-trajectory-and-object-insertion-simulation-test>)

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

Data updated: 2026-03-06T08:58:50.952Z

Evaluation of models performing Generative Video Enhancement on the test split of the Novel Trajectory and Object Insertion Simulation dataset, assessed using Human Evaluation and VLM Evaluation metrics.

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 | Generative Video Enhancement |
| Dataset (including any stated split) | Novel Trajectory and Object Insertion Simulation (test) |
| Metric | Human Eval (%) |
| 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

- [Human Eval (%)](<https://www.sota2.com/research/sota/generative-video-enhancement-on-novel-trajectory-and-object-insertion-simulation-test.md?metric=Human%20Eval%20(%25)>): Higher is better; unit: PERCENT.

- [VLM Eval (%)](<https://www.sota2.com/research/sota/generative-video-enhancement-on-novel-trajectory-and-object-insertion-simulation-test.md?metric=VLM%20Eval%20(%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Human Eval (%) | Result date | Report paper |
| --- | --- | --- | --- |
| DiffusionHarmonizer | 90.11 | Not recorded | 69a5196c2d603e6de3e3c888 |
| DiffusionHarmonizer | 90.1 | Not recorded | 69a5196c2d603e6de3e3c888 |
| DiffusionHarmonizer | 84.28 | Not recorded | 69a5196c2d603e6de3e3c888 |

### DiffusionHarmonizer

Human Eval (%): 90.11. Result ID: 69aa96ef6dbb7075b9547b13.

[Reporting paper](<https://www.sota2.com/research/paper/69a5196c2d603e6de3e3c888.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a5196c2d603e6de3e3c888.md>)

Recorded evaluation configuration: {"Baseline comparison":"Wan-Video V2V"}. This record does not assert independent reproduction.

### DiffusionHarmonizer

Human Eval (%): 90.1. Result ID: 69aa96ef6dbb7075b9547b12.

[Reporting paper](<https://www.sota2.com/research/paper/69a5196c2d603e6de3e3c888.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a5196c2d603e6de3e3c888.md>)

Recorded evaluation configuration: {"Baseline comparison":"InstructPix2Pix"}. This record does not assert independent reproduction.

### DiffusionHarmonizer

Human Eval (%): 84.28. Result ID: 69aa96ef6dbb7075b9547b11.

[Reporting paper](<https://www.sota2.com/research/paper/69a5196c2d603e6de3e3c888.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a5196c2d603e6de3e3c888.md>)

Recorded evaluation configuration: {"Baseline comparison":"SDEdit (SD 3)"}. This record does not assert independent reproduction.

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