The dataset contains procedurally generated images of transparent vessels containing liquid and objects . The data for each image includes segmentation maps, 3d depth maps, and normal maps of of the liquid or object inside the transparent vessel, and the vessel. In addition, the properties of the materials inside the containers are given(color/transparency/roughness/metalness).
In addition, a natural image benchmark for the 3d/depth estimation of objects inside transparent containers is supplied.
3d models of the objects (GTLF) are also supplied.
Variants: TransProteus
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Single-View 3D Reconstruction | XYZNet | Predicting 3D shapes, masks, and … | 2021-09-15 |
Recent papers with results on this dataset: