# 3DoF object manipulation trajectory generation on HOT3D

Source: [3DoF object manipulation trajectory generation on HOT3D](<https://www.sota2.com/research/sota/3dof-object-manipulation-trajectory-generation-on-hot3d>)

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

Data updated: 2026-02-26T05:21:36.951Z

Evaluation of models generating 3DoF object manipulation trajectories on the HOT3D dataset, typically assessed using 3D/2D Average Displacement Error (ADE) and Final Displacement Error (FDE).

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 | 3DoF object manipulation trajectory generation |
| Dataset (including any stated split) | HOT3D |
| Metric | 3D ADE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 12 of 12 |
| 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

- [3D ADE](<https://www.sota2.com/research/sota/3dof-object-manipulation-trajectory-generation-on-hot3d.md?metric=3D%20ADE>): Lower is better; unit: SCALAR.

- [3D FDE](<https://www.sota2.com/research/sota/3dof-object-manipulation-trajectory-generation-on-hot3d.md?metric=3D%20FDE>): Lower is better; unit: SCALAR.

- [2D ADE](<https://www.sota2.com/research/sota/3dof-object-manipulation-trajectory-generation-on-hot3d.md?metric=2D%20ADE>): Lower is better; unit: SCALAR.

- [2D FDE](<https://www.sota2.com/research/sota/3dof-object-manipulation-trajectory-generation-on-hot3d.md?metric=2D%20FDE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | 3D ADE | Result date | Report paper |
| --- | --- | --- | --- |
| Seq2Seq | 0.269 | Not recorded | 68fa79131e209131cea7bfd0 |
| PointLLM (7B) | 0.274 | Not recorded | 68fa79131e209131cea7bfd0 |
| BLIP-2 (2.7B) | 0.278 | Not recorded | 68fa79131e209131cea7bfd0 |
| BLIP-2 (6.7B) | 0.283 | Not recorded | 68fa79131e209131cea7bfd0 |
| BLIP-2 (6.7B) | 0.286 | Not recorded | 68fa79131e209131cea7bfd0 |
| BLIP-2 (2.7B) | 0.288 | Not recorded | 68fa79131e209131cea7bfd0 |
| VILA (8B) | 0.298 | Not recorded | 68fa79131e209131cea7bfd0 |
| MiniGPT-3D (2.7B) | 0.299 | Not recorded | 68fa79131e209131cea7bfd0 |
| VILA (3B) | 0.301 | Not recorded | 68fa79131e209131cea7bfd0 |
| Seq2Seq | 0.302 | Not recorded | 68fa79131e209131cea7bfd0 |
| VILA (8B) | 0.316 | Not recorded | 68fa79131e209131cea7bfd0 |
| VILA (3B) | 0.5 | Not recorded | 68fa79131e209131cea7bfd0 |

### Seq2Seq

3D ADE: 0.269. Result ID: 6995c27f3badfaffe6c54717.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7bfd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"Input":"Image"}. This record does not assert independent reproduction.

### PointLLM (7B)

3D ADE: 0.274. Result ID: 6995c27f3badfaffe6c54722.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7bfd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74c51e209131cea63b44.md>)

[Implementation](<https://github.com/OpenRobotLab/PointLLM>)

Recorded evaluation configuration: {"Input":"Point cloud"}. This record does not assert independent reproduction.

### BLIP-2 (2.7B)

3D ADE: 0.278. Result ID: 6995c27f3badfaffe6c54718.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7bfd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea46fe6.md>)

[Implementation](<https://github.com/salesforce/LAVIS/tree/main/projects/blip2>)

Recorded evaluation configuration: {"Input":"Image"}. This record does not assert independent reproduction.

### BLIP-2 (6.7B)

3D ADE: 0.283. Result ID: 6995c27f3badfaffe6c5471e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7bfd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea46fe6.md>)

[Implementation](<https://github.com/salesforce/LAVIS/tree/main/projects/blip2>)

Recorded evaluation configuration: {"Input":"Image + Depth"}. This record does not assert independent reproduction.

### BLIP-2 (6.7B)

3D ADE: 0.286. Result ID: 6995c27f3badfaffe6c54719.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7bfd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea46fe6.md>)

[Implementation](<https://github.com/salesforce/LAVIS/tree/main/projects/blip2>)

Recorded evaluation configuration: {"Input":"Image"}. This record does not assert independent reproduction.

### BLIP-2 (2.7B)

3D ADE: 0.288. Result ID: 6995c27f3badfaffe6c5471d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7bfd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fb71e209131cea46fe6.md>)

[Implementation](<https://github.com/salesforce/LAVIS/tree/main/projects/blip2>)

Recorded evaluation configuration: {"Input":"Image + Depth"}. This record does not assert independent reproduction.

### VILA (8B)

3D ADE: 0.298. Result ID: 6995c27f3badfaffe6c54720.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7bfd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73311e209131cea5b06b.md>)

[Implementation](<https://github.com/NVlabs/VILA>)

Recorded evaluation configuration: {"Input":"Image + Depth"}. This record does not assert independent reproduction.

### MiniGPT-3D (2.7B)

3D ADE: 0.299. Result ID: 6995c27f3badfaffe6c54721.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7bfd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73161e209131cea5a71d.md>)

[Implementation](<https://github.com/TangYuan96/MiniGPT-3D>)

Recorded evaluation configuration: {"Input":"Point cloud"}. This record does not assert independent reproduction.

### VILA (3B)

3D ADE: 0.301. Result ID: 6995c27f3badfaffe6c5471f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7bfd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73311e209131cea5b06b.md>)

[Implementation](<https://github.com/NVlabs/VILA>)

Recorded evaluation configuration: {"Input":"Image + Depth"}. This record does not assert independent reproduction.

### Seq2Seq

3D ADE: 0.302. Result ID: 6995c27f3badfaffe6c5471c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7bfd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: {"Input":"Image + Depth"}. This record does not assert independent reproduction.

### VILA (8B)

3D ADE: 0.316. Result ID: 6995c27f3badfaffe6c5471b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7bfd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73311e209131cea5b06b.md>)

[Implementation](<https://github.com/NVlabs/VILA>)

Recorded evaluation configuration: {"Input":"Image"}. This record does not assert independent reproduction.

### VILA (3B)

3D ADE: 0.5. Result ID: 6995c27f3badfaffe6c5471a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79131e209131cea7bfd0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73311e209131cea5b06b.md>)

[Implementation](<https://github.com/NVlabs/VILA>)

Recorded evaluation configuration: {"Input":"Image"}. This record does not assert independent reproduction.

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