# Category-level 6D Pose and Size Estimation on REAL275 (test)

Source: [Category-level 6D Pose and Size Estimation on REAL275 (test)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test>)

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

Data updated: 2026-02-26T06:09:51.137Z

Evaluation of Category-level 6D Pose and Size Estimation performance on the test split of the REAL275 dataset, focusing on Mean Average Precision (mAP) metrics derived from various IoU thresholds combined with angular and distance error tolerances.

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 | Category-level 6D Pose and Size Estimation |
| Dataset (including any stated split) | REAL275 (test) |
| Metric | mAP (IoU50) |
| Unit | PERCENT |
| Direction | Higher 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

- [mAP (IoU50)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test.md?metric=mAP%20(IoU50)>): Higher is better; unit: PERCENT.

- [mAP (IoU75, 5deg, 5%)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test.md?metric=mAP%20(IoU75%2C%205deg%2C%205%25)>): Higher is better; unit: PERCENT.

- [mAP (IoU75, 10deg, 5%)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test.md?metric=mAP%20(IoU75%2C%2010deg%2C%205%25)>): Higher is better; unit: PERCENT.

- [mAP (IoU75, 5deg, 10%)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test.md?metric=mAP%20(IoU75%2C%205deg%2C%2010%25)>): Higher is better; unit: PERCENT.

- [mAP (IoU50, 5deg, 20%)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test.md?metric=mAP%20(IoU50%2C%205deg%2C%2020%25)>): Higher is better; unit: PERCENT.

- [mAP (IoU50, 10deg, 10%)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test.md?metric=mAP%20(IoU50%2C%2010deg%2C%2010%25)>): Higher is better; unit: PERCENT.

- [mAP (IoU50, 10deg, 20%)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test.md?metric=mAP%20(IoU50%2C%2010deg%2C%2020%25)>): Higher is better; unit: PERCENT.

- [mAP (IoU75)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test.md?metric=mAP%20(IoU75)>): Higher is better; unit: PERCENT.

- [mAP (5deg, 2cm)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test.md?metric=mAP%20(5deg%2C%202cm)>): Higher is better; unit: PERCENT.

- [mAP (5deg, 5cm)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test.md?metric=mAP%20(5deg%2C%205cm)>): Higher is better; unit: PERCENT.

- [mAP (10deg, 2cm)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test.md?metric=mAP%20(10deg%2C%202cm)>): Higher is better; unit: PERCENT.

- [mAP (10deg, 5cm)](<https://www.sota2.com/research/sota/category-level-6d-pose-and-size-estimation-on-real275-test.md?metric=mAP%20(10deg%2C%205cm)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP (IoU50) | Result date | Report paper |
| --- | --- | --- | --- |
| DualPoseNet | 79.8 | Not recorded | 68fa6a931e209131cea2902e |
| NOCS | 78 | Not recorded | 68fa6a931e209131cea2902e |
| CASS | 77.7 | Not recorded | 68fa6a931e209131cea2902e |
| SPD | 77.3 | Not recorded | 68fa6a931e209131cea2902e |

### DualPoseNet

mAP (IoU50): 79.8. Result ID: 699ac0775698665ec44ea2ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a931e209131cea2902e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a931e209131cea2902e.md>)

[Implementation](<https://github.com/Gorilla-Lab-SCUT/DualPoseNet>)

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

### NOCS

mAP (IoU50): 78. Result ID: 699ac0775698665ec44ea2e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a931e209131cea2902e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65f71e209131cea0d894.md>)

[Implementation](<https://hughw19.github.io/NOCS_CVPR2019>)

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

### CASS

mAP (IoU50): 77.7. Result ID: 699ac0775698665ec44ea2eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a931e209131cea2902e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b431e209131cea2d11d.md>)

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

### SPD

mAP (IoU50): 77.3. Result ID: 699ac0775698665ec44ea2ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a931e209131cea2902e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67f61e209131cea1976b.md>)

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.