AI Paper Atlas

Research map / 3D vision / 3D generation

Zero-shot Inexact CAD Model Alignment from a Single Image

Pattaramanee Arsomngern, Sasikarn Khwanmuang, Matthias Nießner, Supasorn Suwajanakorn

ICCV 2025 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 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
add geometry-aware adapter features fused with DINOv2 in coarse alignment (ablation)coarse alignment · ScanNet25kavg instance accuracy: 18.8 -> 26.0Improved
fuse DINOv2 features with adapter features instead of using adapter features only (omega=1) (ablation)coarse alignment · ScanNet25kavg instance accuracy: 21.0 -> 26.0Improved
add NOC dense alignment refinement after coarse alignment (ablation)Ours · ScanNet25kavg instance accuracy: 26.0 -> 30.1Improved
use NOC dense alignment instead of feature-metric (FM) dense alignment (ablation)Ours · ScanNet25kavg instance accuracy: 26.1 -> 30.1Improved
use feature-metric dense alignment on top of DINOv2 coarse alignment (ablation)DINOv2 coarse · ScanNet25kavg instance accuracy: 18.8 -> 18.8No clear effect
use nearest neighbor matching in adapter feature space instead of directly regressed NOC (NOC-S) for correspondences (ablation)coarse + NOC refinement · ScanNet25kavg instance accuracy: 19.9 -> 30.1Improved
replace DINOv2 with our features in coarse step before NOC refinement (ablation)NOC refinement pipeline · ScanNet25kavg instance accuracy: 24.2 -> 30.1Improved
add depth loss to dense alignment (alone) (ablation)dense alignment · ScanNet25k 9 categoriesavg instance accuracy: 23.93 -> 24.87Improved
add mask loss alone to dense alignment (ablation)dense alignment · ScanNet25k 9 categoriesavg instance accuracy: 23.93 -> 18.92Hurt
add NOC alignment loss alone to dense alignment (ablation)dense alignment · ScanNet25k 9 categoriesavg instance accuracy: 23.93 -> 23.76No clear effect
combine NOC-A, mask and depth losses in dense alignment (ablation)dense alignment · ScanNet25k 9 categoriesavg instance accuracy: 23.93 -> 28.36Improved
adapt our method to 6-DoF with ground-truth scales versus FoundationPoseOurs (for 6D) · ScanNet25kavg instance accuracy: 31.1 -> 38.0Improved

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