Dense Voxel Representation Network for Implicit Scene Completion | IEEE Conference Publication | IEEE Xplore

Dense Voxel Representation Network for Implicit Scene Completion


Abstract:

Implicit scene completion aims to learn an implicit representation of dense point clouds from incomplete ones. Since point clouds are disordered and irregular, some impli...Show More

Abstract:

Implicit scene completion aims to learn an implicit representation of dense point clouds from incomplete ones. Since point clouds are disordered and irregular, some implicit scene completion methods learn representations from voxelized point clouds with sparse convolution. Despite achieving promising results, they lack deep exploration of feature learning on empty voxels, which is beneficial for implicit scene completion task. To address this, we propose a dense voxel representation network for implicit scene completion. First, we design a Bird’s-Eye View (BEV) assisted enhancement module to enhance non-empty voxel features by incorporating the information contained in the learned dense BEV features into them through deformable cross-attention. Second, we construct a feature adaptive completion module to adaptively complete voxel features using deformable self-attention, realizing the transfer of the information from non-empty voxels to empty voxels. Extensive experiments on SemanticKITTI and SemanticPOSS datasets demonstrate our method achieves state-of-the-art performance.
Date of Conference: 15-19 July 2024
Date Added to IEEE Xplore: 30 September 2024
ISBN Information:

ISSN Information:

Conference Location: Niagara Falls, ON, Canada

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.