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

In this paper, we propose a novel network, SVDFormer, to tackle two specificchallenges in point cloud completion: understanding faithful global shapes fromincomplete point clouds and generating high-accuracy local structures. Currentmethods either perceive shape patterns using only 3D coordinates or importextra images with well-calibrated intrinsic parameters to guide the geometryestimation of the missing parts. However, these approaches do not always fullyleverage the cross-modal self-structures available for accurate andhigh-quality point cloud completion. To this end, we first design a Self-viewFusion Network that leverages multiple-view depth image information to observeincomplete self-shape and generate a compact global shape. To reveal highlydetailed structures, we then introduce a refinement module, calledSelf-structure Dual-generator, in which we incorporate learned shape priors andgeometric self-similarities for producing new points. By perceiving theincompleteness of each point, the dual-path design disentangles refinementstrategies conditioned on the structural type of each point. SVDFormer absorbsthe wisdom of self-structures, avoiding any additional paired information suchas color images with precisely calibrated camera intrinsic parameters.Comprehensive experiments indicate that our method achieves state-of-the-artperformance on widely-used benchmarks. Code will be available athttps://github.com/czvvd/SVDFormer.

SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generator