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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We propose a novel method for 3D shape completion from a partial observationof a point cloud. Existing methods either operate on a global latent code,which limits the expressiveness of their model, or autoregressively estimatethe local features, which is highly computationally extensive. Instead, ourmethod estimates the entire local feature field by a single feedforward networkby formulating this problem as a tensor completion problem on the featurevolume of the object. Due to the redundancy of local feature volumes, thistensor completion problem can be further reduced to estimating the canonicalfactors of the feature volume. A hierarchical variational autoencoder (VAE)with tiny MLPs is used to probabilistically estimate the canonical factors ofthe complete feature volume. The effectiveness of the proposed method isvalidated by comparing it with the state-of-the-art method quantitatively andqualitatively. Further ablation studies also show the need to adopt ahierarchical architecture to capture the multimodal distribution of possibleshapes.

Probabilistic Shape Completion by Estimating Canonical Factors with Hierarchical VAE