AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Axolotl3D: a Unified Framework for Faithful 3D Shape Completion

Anita Hu, Maria Shugrina

ECCV 2026 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 2 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
train/test with single-view input, Axolotl3D vs ShapeRAxolotl3D · Toys4k single-view with occlusionF-score: 0.7453 -> 0.9046Improved
multi-view input, Axolotl3D vs ShapeRAxolotl3D · OmniObject3D multi-view with occlusionChamfer distance (x10): 0.1443 (ShapeR) vs 0.1467 (Ours); F-score 0.9532 -> 0.9755Mixed
use ground-truth points vs predicted depthAxolotl3D · Toys4k single-viewF-score: 0.9221 -> 0.7616Hurt
perturb camera parametersAxolotl3D · Toys4k single-view predicted depthF-score: 0.7616 -> 0.7620No clear effect
reduce input points to 2048ShapeR · Toys4k single-view with occlusionF-score: 0.7453 -> 0.6956Hurt
add point cloud condition (ablation)Axolotl3D · Toys4k occlusionF-scoreImproved
add mask-biased cross-attention (ablation)Axolotl3D · Toys4k occlusionF-scoreImproved
use Plucker camera embeddings instead of learned per-view embeddings (ablation)Axolotl3D · Toys4k single-view occlusionF-scoreImproved
skip ICP alignment at evaluationall methods · Toys4kF-scoreHurt

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