# Visual Odometry on TUM RGB-D poor structure, poor texture, far (sequences 5-8)

Source: [Visual Odometry on TUM RGB-D poor structure, poor texture, far (sequences 5-8)](<https://www.sota2.com/research/sota/visual-odometry-on-tum-rgb-d-poor-structure-poor-texture-far-sequences-5-8>)

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

Data updated: 2026-02-26T06:00:17.715Z

Evaluation of Visual Odometry performance using the specified subset (sequences 5-8) of the TUM RGB-D dataset, focusing on poor structure and poor texture conditions.

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 | Visual Odometry |
| Dataset (including any stated split) | TUM RGB-D poor structure, poor texture, far (sequences 5-8) |
| Metric | RMSE (m/s) |
| Unit | TIME |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| 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

- [RMSE (m/s)](<https://www.sota2.com/research/sota/visual-odometry-on-tum-rgb-d-poor-structure-poor-texture-far-sequences-5-8.md?metric=RMSE%20(m%2Fs)>): Lower is better; unit: TIME.

## Recorded results

| Method | RMSE (m/s) | Result date | Report paper |
| --- | --- | --- | --- |
| Weighted sum | 0.123848 | Not recorded | 68fa61971e209131ce9f4ed6 |
| Tykkala's method | 0.129923 | Not recorded | 68fa61971e209131ce9f4ed6 |
| Bounded objective | 0.152104 | Not recorded | 68fa61971e209131ce9f4ed6 |
| Single objective | 0.17046 | Not recorded | 68fa61971e209131ce9f4ed6 |

### Weighted sum

RMSE (m/s): 0.123848. Result ID: 698bcd017a967eddb771737b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61971e209131ce9f4ed6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61971e209131ce9f4ed6.md>)

Recorded evaluation configuration: {"Camera Distance":"Far"}. This record does not assert independent reproduction.

### Tykkala's method

RMSE (m/s): 0.129923. Result ID: 698bcd017a967eddb771737a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61971e209131ce9f4ed6.md>)

Recorded evaluation configuration: {"Camera Distance":"Far"}. This record does not assert independent reproduction.

### Bounded objective

RMSE (m/s): 0.152104. Result ID: 698bcd017a967eddb771737c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61971e209131ce9f4ed6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61971e209131ce9f4ed6.md>)

Recorded evaluation configuration: {"Camera Distance":"Far"}. This record does not assert independent reproduction.

### Single objective

RMSE (m/s): 0.17046. Result ID: 698bcd017a967eddb7717379.

[Reporting paper](<https://www.sota2.com/research/paper/68fa61971e209131ce9f4ed6.md>)

Recorded evaluation configuration: {"Camera Distance":"Far"}. This record does not assert independent reproduction.

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