Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Rethinking Mesh Watermark: Towards Highly Robust and Adaptable Deep 3D Mesh Watermarking (2307.11628v2)

Published 21 Jul 2023 in cs.CR

Abstract: The goal of 3D mesh watermarking is to embed the message in 3D meshes that can withstand various attacks imperceptibly and reconstruct the message accurately from watermarked meshes. The watermarking algorithm is supposed to withstand multiple attacks, and the complexity should not grow significantly with the mesh size. Unfortunately, previous methods are less robust against attacks and lack of adaptability. In this paper, we propose a robust and adaptable deep 3D mesh watermarking Deep3DMark that leverages attention-based convolutions in watermarking tasks to embed binary messages in vertex distributions without texture assistance. Furthermore, our Deep3DMark exploits the property that simplified meshes inherit similar relations from the original ones, where the relation is the offset vector directed from one vertex to its neighbor. By doing so, our method can be trained on simplified meshes but remains effective on large size meshes (size adaptable) and unseen categories of meshes (geometry adaptable). Extensive experiments demonstrate our method remains efficient and effective even if the mesh size is 190x increased. Under mesh attacks, Deep3DMark achieves 10%~50% higher accuracy than traditional methods, and 2x higher SNR and 8% higher accuracy than previous DNN-based methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. Graph spectral domain blind watermarking. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2492–2496. IEEE.
  2. ShapeNet: An Information-Rich 3D Model Repository. Technical Report arXiv:1512.03012 [cs.GR], Stanford University — Princeton University — Toyota Technological Institute at Chicago.
  3. Neural joint source-channel coding. In International Conference on Machine Learning, 1182–1192. PMLR.
  4. ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. In Proc. Computer Vision and Pattern Recognition (CVPR), IEEE.
  5. Implicit fairing of irregular meshes using diffusion and curvature flow. In Seminal Graphics Papers: Pushing the Boundaries, Volume 2, 149–156.
  6. Think Twice Before Detecting GAN-generated Fake Images from their Spectral Domain Imprints. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 7865–7874.
  7. Graspnet-1billion: A large-scale benchmark for general object grasping. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 11444–11453.
  8. Meshnet: Mesh neural network for 3d shape representation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, 8279–8286.
  9. Google. 2017. Draco 3D Data Compression. https://google.github.io/draco/.
  10. Flex-convolution. In Asian Conference on Computer Vision, 105–122. Springer.
  11. Monte carlo convolution for learning on non-uniformly sampled point clouds. ACM Transactions on Graphics (TOG), 37(6): 1–12.
  12. Deep geometric texture synthesis. arXiv preprint arXiv:2007.00074.
  13. Separable Reversible Data Hiding for Encrypted 3D Mesh Models Based on Octree Subdivision and Multi-MSB Prediction. IEEE Transactions on Multimedia.
  14. Blind 3D mesh watermarking for 3D printed model by analyzing layering artifact. IEEE Transactions on Information Forensics and Security, 12(11): 2712–2725.
  15. Subdivision-based mesh convolution networks. ACM Transactions on Graphics (TOG), 41(3): 1–16.
  16. Reversible data hiding in encrypted three-dimensional mesh models. IEEE Transactions on Multimedia, 20(1): 55–67.
  17. ExMeshCNN: An Explainable Convolutional Neural Network Architecture for 3D Shape Analysis. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 795–803.
  18. Meshsnet: Deep multi-scale mesh feature learning for end-to-end tooth labeling on 3d dental surfaces. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 837–845. Springer.
  19. Lindstrom, P.; et al. 1998. Fast and memory efficient polygonal simplification. In IEEE Vis, 279–286. IEEE.
  20. Lindstrom, P.; et al. 1999. Evaluation of memoryless simplification. IEEE Transactions on Visualization and Computer Graphics, 5(2): 98–115.
  21. Relation-shape convolutional neural network for point cloud analysis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8895–8904.
  22. A semi-fragile reversible watermarking for authenticating 3d models in dual domains based on variable direction double modulation. IEEE Transactions on Circuits and Systems for Video Technology, 32(12): 8394–8408.
  23. A general region nesting-based semi-fragile reversible watermarking for authenticating 3D mesh models. IEEE transactions on circuits and systems for video technology, 31(11): 4538–4553.
  24. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, 652–660.
  25. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30.
  26. Embodied hands: Modeling and capturing hands and bodies together. arXiv preprint arXiv:2201.02610.
  27. Shannon, C. E. 1948. A mathematical theory of communication. The Bell system technical journal, 27(3): 379–423.
  28. Dynamic edge-conditioned filters in convolutional neural networks on graphs. In Proceedings of the IEEE conference on computer vision and pattern recognition, 3693–3702.
  29. Perceptual 3D watermarking using mesh saliency. In International Conference on Information Science and Applications, 315–322. Springer.
  30. As-rigid-as-possible surface modeling. In Symposium on Geometry processing, volume 4, 109–116. Citeseer.
  31. The CGAL Project. 2022. CGAL User and Reference Manual. CGAL Editorial Board, 5.5.1 edition.
  32. Tsai, Y.-Y. 2020. Separable reversible data hiding for encrypted three-dimensional models based on spatial subdivision and space encoding. IEEE transactions on multimedia, 23: 2286–2296.
  33. Integrating Coordinate Transformation and Random Sampling Into High-Capacity Reversible Data Hiding in Encrypted Polygonal Models. IEEE Transactions on Dependable and Secure Computing.
  34. Visualizing data using t-SNE. Journal of machine learning research, 9(11).
  35. Graph attention networks. arXiv preprint arXiv:1710.10903.
  36. Deep 3D mesh watermarking with self-adaptive robustness. Cybersecurity, 5(1): 1–14.
  37. Dynamic graph cnn for learning on point clouds. Acm Transactions On Graphics (tog), 38(5): 1–12.
  38. Pointconv: Deep convolutional networks on 3d point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9621–9630.
  39. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1912–1920.
  40. Directionally convolutional networks for 3D shape segmentation. In Proceedings of the IEEE International Conference on Computer Vision, 2698–2707.
  41. Spidercnn: Deep learning on point sets with parameterized convolutional filters. In Proceedings of the European Conference on Computer Vision (ECCV), 87–102.
  42. Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10031–10040.
  43. Distortion design for secure adaptive 3-d mesh steganography. IEEE Transactions on Multimedia, 21(6): 1384–1398.
Citations (2)
View on Semantic Scholar

Summary

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

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