English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Semantic scene completion (SSC) aims to complete a partial 3D scene andpredict its semantics simultaneously. Most existing works adopt the voxelrepresentations, thus suffering from the growth of memory and computation costas the voxel resolution increases. Though a few works attempt to solve SSC fromthe perspective of 3D point clouds, they have not fully exploited thecorrelation and complementarity between the two tasks of scene completion andsemantic segmentation. In our work, we present CasFusionNet, a novel cascadednetwork for point cloud semantic scene completion by dense feature fusion.Specifically, we design (i) a global completion module (GCM) to produce anupsampled and completed but coarse point set, (ii) a semantic segmentationmodule (SSM) to predict the per-point semantic labels of the completed pointsgenerated by GCM, and (iii) a local refinement module (LRM) to further refinethe coarse completed points and the associated labels from a local perspective.We organize the above three modules via dense feature fusion in each level, andcascade a total of four levels, where we also employ feature fusion betweeneach level for sufficient information usage. Both quantitative and qualitativeresults on our compiled two point-based datasets validate the effectiveness andsuperiority of our CasFusionNet compared to state-of-the-art methods in termsof both scene completion and semantic segmentation. The codes and datasets areavailable at: https://github.com/JinfengX/CasFusionNet.

CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion