| Naveen Venkat*1 | Mayank Agarwal*1 | Maneesh Singh | Shubham Tulsiani1 |
| 1Carnegie Mellon University |
|
|
Qualitative results on heldout objects from training categories.
For each object, we consider V=3 input views and compare the reconstruction quality of each method on novel query views. |
|
|
Qualitative results on objects from heldout categories. For each object, we consider V=3 input views and compare the reconstruction quality of each method on novel query views. Note that the model has never seen these categories of objects during training. |