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 explore the task of zero-shot semantic segmentation of 3D shapes by usinglarge-scale off-the-shelf 2D image recognition models. Surprisingly, we findthat modern zero-shot 2D object detectors are better suited for this task thancontemporary text/image similarity predictors or even zero-shot 2D segmentationnetworks. Our key finding is that it is possible to extract accurate 3Dsegmentation maps from multi-view bounding box predictions by using thetopological properties of the underlying surface. For this, we develop theSegmentation Assignment with Topological Reweighting (SATR) algorithm andevaluate it on ShapeNetPart and our proposed FAUST benchmarks. SATR achievesstate-of-the-art performance and outperforms a baseline algorithm by 1.3% and4% average mIoU on the FAUST coarse and fine-grained benchmarks, respectively,and by 5.2% average mIoU on the ShapeNetPart benchmark. Our source code anddata will be publicly released. Project webpage:https://samir55.github.io/SATR/.

SATR: Zero-Shot Semantic Segmentation of 3D Shapes