AI Paper Atlas

Research map / 3D vision / Face and shape

Jigsaw: Learning to Assemble Multiple Fractured Objects

Jiaxin Lu, Yifan Sun, Qixing Huang

NeurIPS 2023 · 3D vision › Face and shape · approach: Optimization-based shape matching · 6 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 Jigsaw's local-geometry, joint segmentation-and-matching assembly framework instead of DGLBreaking Bad everyday · Breaking Bad everydayMAE(R) (degree): 67.8 -> 36.3Improved
Use Jigsaw's assembly framework instead of DGLBreaking Bad everyday · Breaking Bad everydayPA (%): 23.9 -> 57.3Improved
Use Jigsaw's assembly framework instead of DGLBreaking Bad artifact · Breaking Bad artifactMAE(R) (degree): 74.3 -> 45.4Improved
Use Jigsaw's assembly framework instead of DGLBreaking Bad artifact · Breaking Bad artifactPA (%): 9.6 -> 45.6Improved
Jointly train segmentation and matching rather than train them separately (ablation)Jigsaw · Breaking Bad everydayMAE(T) (× 10^-2): 27.2 -> 10.2Improved
Jointly train segmentation and matching rather than train them separately (ablation)Jigsaw · Breaking Bad everydayPA (%): 45.7 -> 47.0Improved
Add self-attention and cross-attention layers (ablation)Jointly trained Jigsaw · Breaking Bad everydayMAE(R) (degree): 44.4 -> 36.3Improved
Add self-attention and cross-attention layers (ablation)Jointly trained Jigsaw · Breaking Bad everydayPA (%): 47.0 -> 57.2Improved
Add rigidity loss (ablation)Jointly trained Jigsaw with attention · Breaking Bad everydayMAE(T) (× 10^-2): 8.9 -> 8.7Improved
Add rigidity loss (ablation)Jointly trained Jigsaw with attention · Breaking Bad everydayPA (%): 57.2 -> 57.3Improved
Use the unmasked primal-dual descriptor rather than the masked primal-dual descriptor (ablation)Jigsaw · Breaking Bad everydayMAE(R) (degree): 0.2° decreaseImproved
Use the unmasked primal-dual descriptor rather than the masked primal-dual descriptor (ablation)Jigsaw · Breaking Bad everydayMAE(T) (× 10^-2): 0.7×10^{-2} improvementImproved

Later papers that compared with this method

5 later accepted papers report Jigsaw as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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