Estimate the pose of next frame given current frame, estimated depth and flow. NOTE: returned pose should be under global coordinate! Returns * pose - 7, shaped pypose.LieTensor (SE3 ltype) under world coordinate predicted pose
(self, frame: T_Data, flow: torch.Tensor | None, depth: torch.Tensor | None)
| 23 | |
| 24 | @abstractmethod |
| 25 | def predict(self, frame: T_Data, flow: torch.Tensor | None, depth: torch.Tensor | None) -> pp.LieTensor: |
| 26 | """ |
| 27 | Estimate the pose of next frame given current frame, estimated depth and flow. |
| 28 | |
| 29 | NOTE: returned pose should be under global coordinate! |
| 30 | |
| 31 | Returns |
| 32 | * pose - 7, shaped pypose.LieTensor (SE3 ltype) under world coordinate |
| 33 | predicted pose of next frame. |
| 34 | """ |
| 35 | ... |
| 36 | |
| 37 | @abstractmethod |
| 38 | def update(self, pose: pp.LieTensor) -> None: |
no outgoing calls
no test coverage detected