AI Paper Atlas

Research map / 3D vision / Face and shape

Puzzle Similarity: A Perceptually-guided Cross-Reference Metric for Artifact Detection in 3D Scene Reconstructions

Nicolai Hermann, Jorge Condor, Piotr Didyk

ICCV 2025 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 4 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 PuzzleSim cross-reference matching instead of CrossScoreartifact localization · Human artifact dataset (12 scenes, mean)Pearson correlation: 0.510 -> 0.615Improved
use PuzzleSim instead of CrossScoreartifact localization · Human artifact dataset (12 scenes, mean)Spearman correlation: 0.378 -> 0.474Improved
use PuzzleSim instead of CrossScoreartifact localization · Human artifact dataset (12 scenes, mean)std of Pearson across scenes: 0.204 -> 0.120Improved
use PuzzleSim instead of no-reference PaQ-2-PiQartifact localization · Human artifact dataset (12 scenes, mean)Pearson correlation: 0.402 -> 0.615Improved
use PuzzleSim instead of CrossScoreartifact localization · Scene stumpPearson correlation: 0.585 -> 0.505Hurt
use PuzzleSim instead of CrossScoreartifact localization · Scene gardenPearson correlation: 0.748 -> 0.675Hurt
use PuzzleSim instead of CrossScoreartifact localization · Scene treehillPearson correlation: 0.300 -> 0.717Improved
use SqueezeNet features instead of VGG (ablation)PuzzleSim · Human artifact alignmentmap qualityNo clear effect
combine three network layers instead of one (ablation)PuzzleSim · Human artifact alignmentmap qualityImproved
use more than three downsamplings of the image resolution (ablation)PuzzleSim · Human artifact alignmentmap qualityNo clear effect
compare patches across all reference positions instead of the same position (ablation)PuzzleSim · camera shiftsrobustnessImproved

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