# Indoor Object Detection on SUN RGB-D (val)

Source: [Indoor Object Detection on SUN RGB-D (val)](<https://www.sota2.com/research/sota/indoor-object-detection-on-sun-rgb-d-val>)

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

Data updated: 2026-02-26T06:09:59.000Z

Evaluation of Indoor Object Detection performance on the validation split of the SUN RGB-D dataset, reporting standard detection metrics including mAP@0.25 and mAP@0.5.

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 | Indoor Object Detection |
| Dataset (including any stated split) | SUN RGB-D (val) |
| Metric | mAP@0.25 |
| 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

- [mAP@0.25](<https://www.sota2.com/research/sota/indoor-object-detection-on-sun-rgb-d-val.md?metric=mAP%400.25>): Higher is better; unit: PERCENT.

- [mAP@0.5](<https://www.sota2.com/research/sota/indoor-object-detection-on-sun-rgb-d-val.md?metric=mAP%400.5>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP@0.25 | Result date | Report paper |
| --- | --- | --- | --- |
| VoteNet (Ours) | 60.5 | Not recorded | 68fa6c781e209131cea34211 |
| VoteNet+ | 59.1 | Not recorded | 68fa6c781e209131cea34211 |
| VoteNet | 57.7 | Not recorded | 68fa6c781e209131cea34211 |

### VoteNet (Ours)

mAP@0.25: 60.5. Result ID: 698f175d3a6c314849f5b2cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c781e209131cea34211.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c781e209131cea34211.md>)

[Implementation](<https://github.com/dvlab-research/DeepVision3D>)

Recorded evaluation configuration: {"Network":"EQ-PointNet++"}. This record does not assert independent reproduction.

### VoteNet+

mAP@0.25: 59.1. Result ID: 698f175d3a6c314849f5b2cb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c781e209131cea34211.md>)

Recorded evaluation configuration: {"Network":"PointNet++","reproduced\_by":"MMDetection3D \[8\]"}. This record does not assert independent reproduction.

### VoteNet

mAP@0.25: 57.7. Result ID: 698f175d3a6c314849f5b2ca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c781e209131cea34211.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c781e209131cea34211.md>)

[Implementation](<https://github.com/dvlab-research/DeepVision3D>)

Recorded evaluation configuration: {"Network":"PointNet++"}. This record does not assert independent reproduction.

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