Research map / Point clouds / Shape and surface completion
AdaCoSeg: Adaptive Shape Co-Segmentation With Group Consistency Loss
Chenyang Zhu, Kai Xu, Siddhartha Chaudhuri, Li Yi, Leonidas J. Guibas, Hao Zhang
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 AdaCoSeg instead of Shu | shape co-segmentation · COSEG Chair | Rand Index: 0.076 -> 0.055 | Improved |
| use AdaCoSeg instead of Shu | shape co-segmentation · COSEG Lamp | Rand Index: 0.069 -> 0.059 | Improved |
| use AdaCoSeg instead of Sidi | shape co-segmentation · COSEG Vase | Rand Index: 0.102 -> 0.189 | Hurt |
| use AdaCoSeg instead of Shu | shape co-segmentation · COSEG Guitar | Rand Index: 0.041 -> 0.032 | Improved |
| apply AdaCoSeg to the initially segmented training shapes | the training-data segmentations · Training-data Chair | Rand Index: 0.21 -> 0.09 | Improved |
| apply AdaCoSeg to the initially segmented training shapes | the training-data segmentations · Training-data Table | Rand Index: 0.27 -> 0.14 | Improved |
| apply AdaCoSeg to the initially segmented training shapes | the training-data segmentations · Training-data Bicycle | Rand Index: 0.31 -> 0.22 | Improved |
| apply AdaCoSeg to the initially segmented training shapes | the training-data segmentations · Training-data Lamp | Rand Index: 0.18 -> 0.16 | Improved |
| apply AdaCoSeg to the initially segmented training shapes | the training-data segmentations · Training-data Car | Rand Index: 0.38 -> 0.27 | Improved |
| apply AdaCoSeg to the initially segmented training shapes | the training-data segmentations · Training-data Plane | Rand Index: 0.24 -> 0.13 | Improved |
| add the part prior network (ablation) | AdaCoSeg · shape co-segmentation | group consistency loss decrease | Improved |
| add random noise when training the part prior (ablation) | AdaCoSeg · shape co-segmentation | training effectiveness | Improved |
Later papers that compared with this method
2 later accepted papers report AdaCoSeg as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Unsupervised Point Cloud Completion and Segmentation by Generative Adversarial Autoencoding Network (NeurIPS 2022 · better on 1 of 1 shared result)
- Unsupervised Point Cloud Object Co-Segmentation by Co-Contrastive Learning and Mutual Attention Sampling (ICCV 2021 · better on 6 of 6 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
- BAE-NET: Branched Autoencoder for Shape Co-Segmentation (ICCV 2019 · similarity 0.88)
- PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentation (CVPR 2019 · similarity 0.88)
- DeepCO3: Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency Detection (CVPR 2019 · similarity 0.87)
- CyCoSeg: A Cyclic Collaborative Framework for Automated Medical Image Segmentation (TPAMI 2021 · similarity 0.86)
- COS3D: Collaborative Open-Vocabulary 3D Segmentation (NeurIPS 2025 · similarity 0.85)
- SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation (NeurIPS 2025 · similarity 0.85)
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.
