AI Paper Atlas

Research map / 3D vision / Face and shape

Combinative Matching for Geometric Shape Assembly

Nahyuk Lee, Juhong Min, Junhong Lee, Chunghyun Park, Minsu Cho

ICCV 2025 · 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
use cosine affinity instead of L2 distance for occupancy (ablation)CMNet · Breaking Bad everyday pairwiseCRD: 0.38 -> 0.28Improved
add orientation loss (ablation)CMNet · Breaking Bad everyday pairwiseCRD: 0.31 -> 0.28Improved
add orientation loss (L2 affinity) (ablation)CMNet · Breaking Bad everyday pairwiseCRD: 0.42 -> 0.38Improved
use equivariant backbone instead of DGCNN point embedding (ablation)CMNet · Breaking Bad everyday pairwiseCRD: 0.74 -> 0.28Improved
use equivariant backbone instead of DGCNN point embedding (ablation)CMNet · Breaking Bad everyday pairwiseRMSE(R): 38.74 -> 12.88Improved
add shape matching branch (ablation)CMNet · Breaking Bad everyday pairwiseCRD: 0.38 -> 0.28Improved
add occupancy matching branch (ablation)CMNet · Breaking Bad everyday pairwiseCRD: 0.35 -> 0.28Improved
add combinative (shape plus occupancy) matching vs prior state of the art PMTRPMTR · Breaking Bad everyday pairwiseCRD: 0.39 -> 0.28Improved
use CMNet instead of PMTRPMTR · Breaking Bad artifact pairwiseCRD: 0.60 -> 0.49Improved
use CMNet instead of PMTR in everyday-to-artifact transferPMTR · Breaking Bad transferCRD: 0.82 -> 0.74Improved
use CMNet instead of PMTR for multi-part assemblyPMTR · Breaking Bad multi-part everydayPA_CRD: 66.95 -> 73.88Improved
use CMNet instead of Jigsaw for translation errorJigsaw · Breaking Bad everyday pairwiseRMSE(T): 2.73 -> 3.78Hurt

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