AI Paper Atlas

Research map / 3D vision / Face and shape

TORA: Topological Representation Alignment for 3D Shape Assembly

Nahyuk Lee, Zhiang Chen, Marc Pollefeys, Sunghwan Hong

ECCV 2026 · 3D vision › Face and shape · approach: Optimization-based shape matching · 3 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
add CKA topological alignment to RPFRPF · Breaking Bad Everyday (21-33 parts)Part accuracy (%): 62.1 -> 71.7Improved
add token-wise cosine alignment to RPFRPF · Breaking Bad Everyday (2-20 parts)Part accuracy (%): 93.2 -> 95.7Improved
add CKA alignment to RPFRPF · PartNet-AssemblyPart accuracy (%): 59.8 -> 69.1Improved
add NT-Xent alignment to RPF (ablation)RPF · TwoByTwoPart accuracy (%): 65.4 -> 60.4Hurt
replace cosine alignment with CKA (ablation)TORA · TwoByTwoPart accuracy (%): 68.9 -> 71.5Improved
add cos-dist loss on top of CKA (ablation)TORA (CKA) · TwoByTwoPart accuracy (%): 71.5 -> 70.0Hurt
add NT-Xent loss on top of CKA (ablation)TORA (CKA) · TwoByTwoPart accuracy (%): 71.5 -> 68.5Hurt
add both cos-dist and NT-Xent on top of CKA (ablation)TORA (CKA) · TwoByTwoPart accuracy (%): 71.5 -> 67.7Hurt
add CKA alignment to RPF (zero-shot)RPF · Zero-shot from Breaking Bad Everyday: FRACTURAPart accuracy (%): 68.1 -> 76.0Improved
add NT-Xent alignment to RPF (zero-shot) (ablation)RPF · Zero-shot from Breaking Bad Everyday: Breaking Bad ArtifactPart accuracy (%): 88.3 -> 87.0Hurt
use CKA instead of cosine with weak teacher PatchAlign3D (ablation)TORA · TwoByTwoPart accuracy (%): 66.0 -> 68.4Improved
align at deeper layer (l*=5) instead of early layers (ablation)TORA · Breaking BadPart accuracy (%)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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