In this paper, we propose a novel design ofSparse Steerable Convolution (SS-Conv)toaddress theshortcoming; SS-Convgreatly accelerates steerable convolution with sparse tensors, while strictly preserving the property of SE(3)-equivariance. Based on SS-Conv, we propose a general pipeline for precise estimation of object poses, wherein a key design is a Feature-Steering module that takes the full advantage of SE(3)-equivariance and is able to conduct an efficient pose refinement.

Despitetheirsuccess,INRsoftenintroducehard to control inductive bias (i.e., the solution surface can exhibit unexplainable behaviours),havecostlyinference,andareslowtotrain.