Results for RPGN
Submission data
| Full name | Regional Purity Guided Network |
| Publication title | Learning Regional Purity for Instance Segmentation on 3D Point Clouds |
| Publication authors | Shichao Dong, Guosheng Lin, Tzu-Yi Hung |
| Publication venue | ECCV 2022 |
| Publication URL | https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136900055.pdf |
| Input Data Types | Uses Color,Uses Geometry Uses 3D |
| Programming language(s) | C++ with CUDA |
| Hardware | RTX3090 |
| Submission creation date | 25 Jan, 2021 |
| Last edited | 10 Nov, 2022 |
| Last uploaded | 17 Feb, 2021 |
3D semantic instance results
| Info | avg ap 25% | bathtub | bed | bookshelf | cabinet | chair | counter | curtain | desk | door | otherfurniture | picture | refrigerator | shower curtain | sink | sofa | table | toilet | window |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.806 | 1.000 | 0.992 | 0.789 | 0.723 | 0.891 | 0.650 | 0.810 | 0.832 | 0.665 | 0.699 | 0.658 | 0.700 | 1.000 | 0.881 | 0.832 | 0.774 | 0.997 | 0.613 |