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

CAD programs are a popular way to compactly encode shapes as a sequence ofoperations that are easy to parametrically modify. However, without sufficientsemantic comments and structure, such programs can be challenging tounderstand, let alone modify. We introduce the problem of semantic commentingCAD programs, wherein the goal is to segment the input program into code blockscorresponding to semantically meaningful shape parts and assign a semanticlabel to each block. We solve the problem by combining program parsing withvisual-semantic analysis afforded by recent advances in foundational languageand vision models. Specifically, by executing the input programs, we createshapes, which we use to generate conditional photorealistic images to make useof semantic annotators for such images. We then distill the information acrossthe images and link back to the original programs to semantically comment onthem. Additionally, we collected and annotated a benchmark dataset, CADTalk,consisting of 5,280 machine-made programs and 45 human-made programs withground truth semantic comments to foster future research. We extensivelyevaluated our approach, compared to a GPT-based baseline approach, and anopen-set shape segmentation baseline, i.e., PartSLIP, and reported an 83.24%accuracy on the new CADTalk dataset. Project page:https://enigma-li.github.io/CADTalk/.

CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs