Research map / Point clouds / Shape and surface completion
Neural Shape Mating: Self-Supervised Object Assembly With Adversarial Shape Priors
Yun-Chun Chen, Haoda Li, Dylan Turpin, Alec Jacobson, Animesh Garg
Check 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 NSM rather than GNN Assembly | pairwise geometric shape mating · Solid Shape Mating | MAE (R): 30.42 -> 7.61 | Improved |
| Use NSM rather than GNN Assembly | pairwise geometric shape mating · Shell Shape Mating | MAE (R): 38.49 -> 14.52 | Improved |
| Use NSM rather than GNN Assembly | pairwise geometric shape mating · Unseen categories (box and bag), solid | MAE (R): 46.52 -> 13.74 | Improved |
| Use NSM rather than GNN Assembly | pairwise geometric shape mating · Unseen cut type (parabolic), solid | MAE (R): 43.91 -> 13.46 | Improved |
| Add adversarial learning losses L_adv and L_G (ablation) | Neural Shape Mating (NSM) · Solid Shape Mating | MAE (R): 15.04 -> 7.61 | Improved |
| Add adversarial learning losses L_adv and L_G (ablation) | Neural Shape Mating (NSM) · Shell Shape Mating | MAE (R): 18.63 -> 14.52 | Improved |
| Add implicit shape reconstruction loss L_SDF (ablation) | Neural Shape Mating (NSM) · Solid Shape Mating | MAE (R): 11.42 -> 7.61 | Improved |
| Add implicit shape reconstruction loss L_SDF (ablation) | Neural Shape Mating (NSM) · Shell Shape Mating | MAE (R): 17.44 -> 14.52 | Improved |
| Add pose prediction loss L_pose (ablation) | Neural Shape Mating (NSM) · Solid Shape Mating | MAE (R): 85.09 -> 7.61 | Improved |
| Add pose prediction loss L_pose (ablation) | Neural Shape Mating (NSM) · Shell Shape Mating | MAE (R): 93.02 -> 14.52 | Improved |
Closest papers by meaning
- Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing (CVPR 2024 · similarity 0.89)
- Neural Assembler: Learning to Generate Fine-Grained Robotic Assembly Instructions from Multi-View Images (AAAI 2025 · similarity 0.88)
- 3D Geometric Shape Assembly via Efficient Point Cloud Matching (ICML 2024 · similarity 0.88)
- Imagine: Image-Guided 3D Part Assembly with Structure Knowledge Graph (AAAI 2025 · similarity 0.87)
- BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assembly (ICML 2025 · similarity 0.87)
- Category-Level Multi-Part Multi-Joint 3D Shape Assembly (CVPR 2024 · similarity 0.87)
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.
