Papers
Topics
Authors
Recent
2000 character limit reached

G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping (2405.06828v1)

Published 10 May 2024 in cs.CV

Abstract: This paper proposes a novel task named "3D part grouping". Suppose there is a mixed set containing scattered parts from various shapes. This task requires algorithms to find out every possible combination among all the parts. To address this challenge, we propose the so called Gradient Field-based Auto-Regressive Sampling framework (G-FARS) tailored specifically for the 3D part grouping task. In our framework, we design a gradient-field-based selection graph neural network (GNN) to learn the gradients of a log conditional probability density in terms of part selection, where the condition is the given mixed part set. This innovative approach, implemented through the gradient-field-based selection GNN, effectively captures complex relationships among all the parts in the input. Upon completion of the training process, our framework becomes capable of autonomously grouping 3D parts by iteratively selecting them from the mixed part set, leveraging the knowledge acquired by the trained gradient-field-based selection GNN. Our code is available at: https://github.com/J-F-Cheng/G-FARS-3DPartGrouping.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Label-efficient semantic segmentation with diffusion models. arXiv preprint arXiv:2112.03126, 2021.
  2. Neural combinatorial optimization with reinforcement learning. arXiv preprint arXiv:1611.09940, 2016.
  3. Christian Blum. Ant colony optimization: Introduction and recent trends. Physics of Life reviews, 2(4):353–373, 2005.
  4. Jing-Chao Chen. Dijkstra’s shortest path algorithm. Journal of formalized mathematics, 15(9):237–247, 2003.
  5. A mixed samples-driven methodology based on denoising diffusion probabilistic model for identifying damage in carbon fiber composite structures. IEEE Transactions on Instrumentation and Measurement, 2023.
  6. Score-pa: Score-based 3d part assembly. arXiv preprint arXiv:2309.04220, 2023.
  7. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555, 2014.
  8. Ant colony optimization. IEEE computational intelligence magazine, 1(4):28–39, 2006.
  9. Stephanie Forrest. Genetic algorithms. ACM computing surveys (CSUR), 28(1):77–80, 1996.
  10. Genetic algorithms and their applications. In Springer handbook of engineering statistics, pages 635–674. Springer, 2023.
  11. An improved adaptive genetic algorithm. In SHS Web of Conferences, page 01044. EDP Sciences, 2022.
  12. V Haripriya et al. The performance optimization of approximate minimum spanning tree for the different mobility model. In 2023 International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE), pages 1–6. IEEE, 2023.
  13. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  14. John H Holland. Genetic algorithms. Scientific american, 267(1):66–73, 1992.
  15. Generative 3d part assembly via dynamic graph learning. Advances in Neural Information Processing Systems, 33:6315–6326, 2020.
  16. Dijkstra’s shortest path algorithm serial and parallel execution performance analysis. In 2012 proceedings of the 35th international convention MIPRO, pages 1811–1815. IEEE, 2012.
  17. Extending dijkstra’s shortest path algorithm for software defined networking. In The 16th Asia-Pacific Network Operations and Management Symposium, pages 1–4. IEEE, 2014.
  18. Donald B Johnson. A note on dijkstra’s shortest path algorithm. Journal of the ACM (JACM), 20(3):385–388, 1973.
  19. Semiaco: A semi-supervised feature selection based on ant colony optimization. Expert Systems with Applications, 214:119130, 2023.
  20. Ant colony optimization-enabled cnn deep learning technique for accurate detection of cervical cancer. BioMed Research International, 2023, 2023.
  21. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  22. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
  23. Score-based point cloud denoising. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4583–4592, 2021.
  24. Learning to group: A bottom-up framework for 3d part discovery in unseen categories. arXiv preprint arXiv:2002.06478, 2020.
  25. Reinforcement learning for combinatorial optimization: A survey. Computers & Operations Research, 134:105400, 2021.
  26. Partnet: A large-scale benchmark for fine-grained and hierarchical part-level 3d object understanding. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 909–918, 2019.
  27. Dit-3d: Exploring plain diffusion transformers for 3d shape generation. arXiv preprint arXiv:2307.01831, 2023.
  28. Rgl-net: A recurrent graph learning framework for progressive part assembly. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 78–87, 2022.
  29. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 652–660, 2017.
  30. Modification of dijkstra’s algorithm for safest and shortest path during emergency evacuation. Applied Mathematical Sciences, 9(31):1531–1541, 2015.
  31. Self-attention with relative position representations. arXiv preprint arXiv:1803.02155, 2018.
  32. Learning gradient fields for molecular conformation generation. In International Conference on Machine Learning, pages 9558–9568. PMLR, 2021.
  33. Masked label prediction: Unified message passing model for semi-supervised classification. arXiv preprint arXiv:2009.03509, 2020.
  34. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456, 2020.
  35. Genetic algorithms: A survey. computer, 27(6):17–26, 1994.
  36. Learning shape abstractions by assembling volumetric primitives. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2635–2643, 2017.
  37. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  38. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.
  39. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (tog), 38(5):1–12, 2019.
  40. Pq-net: A generative part seq2seq network for 3d shapes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 829–838, 2020.
  41. Graph transformer networks. Advances in neural information processing systems, 32, 2019.
  42. 3d part assembly generation with instance encoded transformer. IEEE Robotics and Automation Letters, 7(4):9051–9058, 2022.
  43. Parameter adaptation-based ant colony optimization with dynamic hybrid mechanism. Engineering Applications of Artificial Intelligence, 114:105139, 2022.
  44. 3d-prnn: Generating shape primitives with recurrent neural networks. In Proceedings of the IEEE International Conference on Computer Vision, pages 900–909, 2017.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now

Whiteboard

Video Overview

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Tweets

Sign up for free to view the 2 tweets with 0 likes about this paper.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up for Free