AI Paper Atlas

Research map / 3D vision / Face and shape

Jigsaw++: Imagining Complete Shape Priors for Object Reassembly

Jiaxin Lu, Gang Hua, Qixing Huang

ICCV 2025 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 7 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 Jigsaw++ shape priorJigsaw · Breaking Bad (everyday)Chamfer distance (x10^-3): 10.5 -> 4.5Improved
add Jigsaw++ shape priorSE(3) · Breaking Bad (everyday)Chamfer distance (x10^-3): 22.4 -> 14.3Improved
add Jigsaw++ shape priorSE(3) · Breaking Bad (everyday)precision (%): 20.2 -> 37.8Improved
add Jigsaw++ shape priorJigsaw · Breaking Bad (everyday)recall (%): 42.7 -> 49.5Improved
add Jigsaw++ shape priorDGL · PartNet LampChamfer distance: 68.8 -> 46.3Improved
add Jigsaw++ shape priorDGL · PartNet Chairprecision (%): 21.5 -> 52.0Improved
remove 20% of pieces from inputJigsaw++ · Breaking Bad BottleChamfer distance (x10^-3): 1.8 -> 2.0No clear effect
remove 20% of pieces from inputJigsaw++ · Breaking Bad Bottleprecision (%): 61.0 -> 59.5No clear effect
use generated shape prior (GT matching) in Jigsaw's global alignmentJigsaw · Breaking Bad fracture assemblyMAE(R) (degree): 36.3 -> 17.8Improved
add 20% noise to shape prior matchingJigsaw++ assembly · Breaking Bad fracture assemblyMAE(R) (degree): 17.8 -> 18.2No clear effect
use retargeting instead of conditional generation fine-tuning (ablation)Jigsaw++ · Breaking Bad (everyday)precision (%): 46.3 -> 48.7Improved
reverse sampling steps k=1/10 versus full reverse sampling (ablation)Jigsaw++ retargeting · Breaking Badreconstruction qualityImproved

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