MCPcopy Create free account
hub / github.com/openai/point-e / predict_sdf

Method predict_sdf

point_e/models/sdf.py:61–69  ·  view source on GitHub ↗

Predict the SDF at the query points given the encoded point clouds. Each query point should be treated independently, only conditioning on the point clouds themselves.

(
        self, x: torch.Tensor, encoded: Optional[Dict[str, torch.Tensor]]
    )

Source from the content-addressed store, hash-verified

59
60 @abstractmethod
61 def predict_sdf(
62 self, x: torch.Tensor, encoded: Optional[Dict[str, torch.Tensor]]
63 ) -> torch.Tensor:
64 """
65 Predict the SDF at the query points given the encoded point clouds.
66
67 Each query point should be treated independently, only conditioning on
68 the point clouds themselves.
69 """
70
71
72class CrossAttentionPointCloudSDFModel(PointCloudSDFModel):

Callers 1

forwardMethod · 0.95

Calls

no outgoing calls

Tested by

no test coverage detected