AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Autoregressive 3D Shape Generation via Canonical Mapping

An-Chieh Cheng, Xueting Li, Sifei Liu, Min Sun, Ming-Hsuan Yang

ECCV 2022 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 36 citations (OpenAlex)

Read the paperCheck 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 canonical grouping instead of uniform grouping (G=128) (ablation)Ours · ShapeNet Chair auto-encodingChamfer distance: 7.676 -> 6.177Improved
use canonical grouping instead of uniform grouping (G=16) (ablation)Ours · ShapeNet Chair auto-encodingChamfer distance: 8.646 -> 7.542Improved
use canonical grouping instead of uniform grouping (G=256) (ablation)Ours · ShapeNet Chair auto-encodingChamfer distance: 7.278 -> 7.933Hurt
increase groups from 128 to 256 with canonical grouping (ablation)Ours · ShapeNet Chair auto-encodingChamfer distance: 6.177 -> 7.933Hurt
add dimension reduction 256->4 to codebook lookup (global codebook) (ablation)Ours · ShapeNet Chair auto-encodingChamfer distance: 7.139 -> 6.298Improved
add grouped codebook on top of 256->4 reduction (ablation)Ours · ShapeNet Chair auto-encodingChamfer distance: 6.298 -> 6.177Improved
add dimension reduction and grouped codebook (ablation)Ours · ShapeNet Chair auto-encodingCodebook usage (%): 11.72 -> 79.28Improved
use Fibonacci spiral order instead of random order (ablation)Ours · ShapeNet Chair unconditional generationMMD-CD: 7.44 -> 7.37Improved
use inverse spiral instead of spiral order (ablation)Ours · ShapeNet Chair unconditional generationMMD-CD: 7.37 -> 7.17Improved
raise top-p from 0.85 to 0.92 (ablation)Ours · ShapeNet Chair unconditional generationMMD-CD: 7.70 -> 7.37Improved
raise top-p from 0.92 to 0.99 (ablation)Ours · ShapeNet Chair unconditional generationCOV-CD (%): 45.77 -> 44.86Mixed
raise sampling temperature from t=1 to t=3 (ablation)Ours · ShapeNet Chair shape completionTMD: 6.553 -> 13.341Improved

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