AI Paper Atlas

Research map / Point clouds / Shape and surface completion

UNIST: Unpaired Neural Implicit Shape Translation Network

Qimin Chen, Johannes Merz, Aditya Sanghi, Hooman Shayani, Ali Mahdavi-Amiri, Hao Zhang

CVPR 2022 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 15 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 position-aware latent grids instead of regular holistic encoding (ablation)UNIST shape translation · 2D font translation: Solid ↔ Dotted, Regular ↔ Italic, Regular ↔ Bold, Sharp ↔ Smoothpreservation of local geometric featuresImproved
Use position-aware latent grids instead of regular holistic encoding (ablation)UNIST shape translation · 3D Chair ↔ Table, Armrest, and Tall table ↔ Short tablepreservation of geometric and structural featuresImproved
Use position-aware encoding instead of regular encoding (ablation)UNIST · A ↔ HMSE: 0.184 -> 0.215Hurt
Use position-aware encoding instead of regular encoding (ablation)UNIST · A ↔ HIoU: 0.507 -> 0.441Hurt
Use position-aware encoding instead of regular encoding (ablation)UNIST · G ↔ RMSE: 0.197 -> 0.211Hurt
Use position-aware encoding instead of regular encoding (ablation)UNIST · G ↔ RIoU: 0.493 -> 0.452Hurt
Use position-aware encoding instead of regular encoding (ablation)UNIST · M ↔ NMSE: 0.201 -> 0.233Hurt
Use position-aware encoding instead of regular encoding (ablation)UNIST · M ↔ NIoU: 0.508 -> 0.433Hurt
Use position-aware encoding instead of regular encoding (ablation)UNIST · Chair with/without Armrestone-sided CD: 0.0255 -> 0.0234; 0.0267 -> 0.0235Improved
Use position-aware encoding instead of regular encoding (ablation)UNIST · Chair ↔ Tableuser preference: ranked 1st votes: 31.34% -> 38.11%; 27.78% -> 36.28%Improved
Represent shapes as neural implicit fields rather than point cloudsUNIST versus LOGAN · 2D shape translationvisual translation quality and fine/topological feature reproductionImproved
Translate on latent grids rather than holistic latent vectors (ablation)UNIST · unpaired shape translationspatial feature and local-detail preservationImproved

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