The Matterport3D dataset is a large RGB-D dataset for scene understanding in indoor environments. It contains 10,800 panoramic views inside 90 real building-scale scenes, constructed from 194,400 RGB-D images. Each scene is a residential building consisting of multiple rooms and floor levels, and is annotated with surface construction, camera poses, and semantic segmentation.
Variants: Matterport3D
This dataset is used in 3 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| Semantic Segmentation | SFSS-MMSI (RGB+Depth+Normal) | Single Frame Semantic Segmentation Using … | 2023-08-18 |
| Semantic Segmentation | SFSS-MMSI (RGB+Depth) | Single Frame Semantic Segmentation Using … | 2023-08-18 |
| Semantic Segmentation | SFSS-MMSI (RGB+Normal) | Single Frame Semantic Segmentation Using … | 2023-08-18 |
| Semantic Segmentation | SFSS-MMSI (RGB Only) | Single Frame Semantic Segmentation Using … | 2023-08-18 |
| Depth Estimation | UniFuse | UniFuse: Unidirectional Fusion for 360$^{\circ}$ … | 2021-02-06 |
| Depth Completion | DM-LRN-b4 | Decoder Modulation for Indoor Depth … | 2020-05-18 |
| Depth Completion | SA+SSIM+BC | Indoor Depth Completion with Boundary … | 2019-08-22 |
Recent papers with results on this dataset: