Research map / 3D vision / Face and shape
Jigsaw: Learning to Assemble Multiple Fractured Objects
Jiaxin Lu, Yifan Sun, Qixing Huang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use Jigsaw's local-geometry, joint segmentation-and-matching assembly framework instead of DGL | Breaking Bad everyday · Breaking Bad everyday | MAE(R) (degree): 67.8 -> 36.3 | Improved |
| Use Jigsaw's assembly framework instead of DGL | Breaking Bad everyday · Breaking Bad everyday | PA (%): 23.9 -> 57.3 | Improved |
| Use Jigsaw's assembly framework instead of DGL | Breaking Bad artifact · Breaking Bad artifact | MAE(R) (degree): 74.3 -> 45.4 | Improved |
| Use Jigsaw's assembly framework instead of DGL | Breaking Bad artifact · Breaking Bad artifact | PA (%): 9.6 -> 45.6 | Improved |
| Jointly train segmentation and matching rather than train them separately (ablation) | Jigsaw · Breaking Bad everyday | MAE(T) (× 10^-2): 27.2 -> 10.2 | Improved |
| Jointly train segmentation and matching rather than train them separately (ablation) | Jigsaw · Breaking Bad everyday | PA (%): 45.7 -> 47.0 | Improved |
| Add self-attention and cross-attention layers (ablation) | Jointly trained Jigsaw · Breaking Bad everyday | MAE(R) (degree): 44.4 -> 36.3 | Improved |
| Add self-attention and cross-attention layers (ablation) | Jointly trained Jigsaw · Breaking Bad everyday | PA (%): 47.0 -> 57.2 | Improved |
| Add rigidity loss (ablation) | Jointly trained Jigsaw with attention · Breaking Bad everyday | MAE(T) (× 10^-2): 8.9 -> 8.7 | Improved |
| Add rigidity loss (ablation) | Jointly trained Jigsaw with attention · Breaking Bad everyday | PA (%): 57.2 -> 57.3 | Improved |
| Use the unmasked primal-dual descriptor rather than the masked primal-dual descriptor (ablation) | Jigsaw · Breaking Bad everyday | MAE(R) (degree): 0.2° decrease | Improved |
| Use the unmasked primal-dual descriptor rather than the masked primal-dual descriptor (ablation) | Jigsaw · Breaking Bad everyday | MAE(T) (× 10^-2): 0.7×10^{-2} improvement | Improved |
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.
- Interact3D: Compositional 3D Generation of Interactive Objects (ECCV 2026 · better on 3 of 3 shared results)
- PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify (ICLR 2025 · better on 7 of 8 shared results)
- Combinative Matching for Geometric Shape Assembly (ICCV 2025 · better on 4 of 5 shared results)
- Jigsaw++: Imagining Complete Shape Priors for Object Reassembly (ICCV 2025 · better on 5 of 5 shared results)
- GARF: Learning Generalizable 3D Reassembly for Real-World Fractures (ICCV 2025 · better on 3 of 3 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
- Scalable Geometric Fracture Assembly via Co-creation Space among Assemblers (AAAI 2024 · similarity 0.90)
- Jigsaw++: Imagining Complete Shape Priors for Object Reassembly (ICCV 2025 · similarity 0.90)
- The Missing GAP: From Solving Square Jigsaw Puzzles to Handling Real World Archaeological Fragments (CVPR 2026 · similarity 0.89)
- PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify (ICLR 2025 · similarity 0.88)
- Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving (NeurIPS 2024 · similarity 0.86)
- 3DPGS: 3D Probabilistic Graph Search for Archaeological Piece Grouping (AAAI 2025 · similarity 0.84)
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.
