atlas

Research map / 3D vision / Face and shape

ShapeTalk: A Language Dataset and Framework for 3D Shape Edits and Deformations

CVPR 2023 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 17 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use ChangeIt3D instead of Neighbor-SearchPC-AE shape editing · Chairs, tables, and lampsLAB: 12.0 -> 35.1Helped
Use ChangeIt3D instead of the Monolithic modelPC-AE shape editing · Chairs, tables, and lampsGD: 0.76 -> 0.33Helped
Use ChangeIt3D instead of Neighbor-SearchPC-AE shape editing · Chairs, tables, and lampsl-GD: 1.02 -> 0.99Helped
Decouple the edit latent into a direction and magnitude (ablation)ChangeIt3D · Chairs, tables, and lampsGD: 0.45 -> 0.33Helped
Use self-contrast against the original input instead of a separate ground-truth target (ablation)ChangeIt3D · Chairs, tables, and lampsGD: 0.43 -> 0.33Helped
Use self-contrast against the original input instead of a separate ground-truth target (ablation)ChangeIt3D · Chairs, tables, and lampsLAB: 43.5 -> 35.1Hurt
Train and evaluate the listener on all utterances for a context instead of one utterance (ablation)ShapeTalk neural listeners · ShapeTalk test setaccuracy: 71.3 -> 81.5Helped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy