# 3D Amodal Object Detection on SUN RGB-D (test)

Source: [3D Amodal Object Detection on SUN RGB-D (test)](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test>)

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

Data updated: 2026-02-26T05:38:59.900Z

Evaluation of 3D amodal object detection performance on the test split of the SUN RGB-D dataset, reporting class-specific metrics and overall mAP.

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 | 3D amodal object detection |
| Dataset (including any stated split) | SUN RGB-D (test) |
| Metric | Chair AP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Chair AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Chair%20AP>): Higher is better; unit: PERCENT.

- [Bed AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Bed%20AP>): Higher is better; unit: PERCENT.

- [Sofa AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Sofa%20AP>): Higher is better; unit: PERCENT.

- [Table AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Table%20AP>): Higher is better; unit: PERCENT.

- [Desk AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Desk%20AP>): Higher is better; unit: PERCENT.

- [Toilet AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Toilet%20AP>): Higher is better; unit: PERCENT.

- [Monitor AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Monitor%20AP>): Higher is better; unit: PERCENT.

- [Bathtub AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Bathtub%20AP>): Higher is better; unit: PERCENT.

- [Sink AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Sink%20AP>): Higher is better; unit: PERCENT.

- [Bookshelf AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Bookshelf%20AP>): Higher is better; unit: PERCENT.

- [Lamp AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Lamp%20AP>): Higher is better; unit: PERCENT.

- [Dresser AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Dresser%20AP>): Higher is better; unit: PERCENT.

- [Blackboard AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Blackboard%20AP>): Higher is better; unit: PERCENT.

- [Nightstand AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Nightstand%20AP>): Higher is better; unit: PERCENT.

- [Cabinet AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Cabinet%20AP>): Higher is better; unit: PERCENT.

- [Shelf AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Shelf%20AP>): Higher is better; unit: PERCENT.

- [Curtain AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Curtain%20AP>): Higher is better; unit: PERCENT.

- [Pillow AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Pillow%20AP>): Higher is better; unit: PERCENT.

- [Whiteboard AP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=Whiteboard%20AP>): Higher is better; unit: PERCENT.

- [mAP](<https://www.sota2.com/research/sota/3d-amodal-object-detection-on-sun-rgb-d-test.md?metric=mAP>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Chair AP | Result date | Report paper |
| --- | --- | --- | --- |
| Deep Sliding Shapes | 78.8 | Not recorded | 68fa62611e209131ce9f8f21 |
| Sliding Shapes | 42.09 | Not recorded | 68fa62611e209131ce9f8f21 |

### Deep Sliding Shapes

Chair AP: 78.8. Result ID: 698bd70d7a967eddb771b92a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa62611e209131ce9f8f21.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62611e209131ce9f8f21.md>)

[Implementation](<http://dss.cs.princeton.edu/>)

Recorded evaluation configuration: {"Architecture":"3D ConvNet"}. This record does not assert independent reproduction.

### Sliding Shapes

Chair AP: 42.09. Result ID: 698bd70d7a967eddb771b929.

[Reporting paper](<https://www.sota2.com/research/paper/68fa62611e209131ce9f8f21.md>)

Recorded evaluation configuration: {"Features":"hand-crafted"}. This record does not assert independent reproduction.

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