Stray Animal IP Design and Commercialization Based on Generative Models

Yantong Dong

doi:10.6911/

Authors

Yantong Dong Basis International School Park Lane Harbour, Huizhou, China

DOI:

https://doi.org/10.6911/

Keywords:

Generative Models, Stray Animal IP.

Abstract

We propose this research to establish an integrated IP generation and commercialisation system for rescuing stray animals, based on diffusion models. By integrating ControlNet for skeletal constraints and latent-space interpolation, the system enables millimetre-level precision by reconstructing animal characteristics, compressing the IP design cycle from months to 30 minutes. It generates derivative results, dynamic rehabilitation diaries, and NFT digital collectable content to create emotional engagement. In addition, it creates a decentralised commercial model with blockchain infrastructure that automatically distributes sales revenue to support physical rescue operations such as treatment and sterilisation. This creates a closed loop of "emotional connection, commercial response and life-saving". The prototype solution utilises ethical technological design to ensure that the pre-eminence of virtual IP wealth does not threaten earthly challenges and can serve as a scalable model for AI initiatives for social good.

Downloads

Download data is not yet available.

References

[1] Pi, R., & Shan, L. (2025). Synthetic lung X-ray generation through cross-attention and affinity transformation. arXiv preprint arXiv:2503.07209.

[2] Zhou, X., Shan, L., & Gui, X. (2025). DynRsl-VLM: Enhancing autonomous driving perception with dynamic resolution vision-language models. arXiv preprint arXiv:2503.11265.

[3] Yi, Q., & Shan, L. (2025). GeoLocSFT: Efficient visual geolocation via supervised fine-tuning of multimodal foundation models. arXiv preprint arXiv:2506.01277.

[4] Sun, C., Li, W., Li, X., & et al. (2025). Gmm-based comprehensive feature extraction and relative distance preservation for few-shot cross-modal retrieval. arXiv preprint arXiv:2505.13306.

[5] Liu, S., & Shan, L. (2025). NeuroVoxel-LM: Language-aligned 3D perception via dynamic voxelization and meta-embedding. arXiv preprint arXiv:2507.20110.

[6] Wang, X., & Shan, L. (2025). GDGS: 3D Gaussian splatting via geometry-guided initialization and dynamic density control. arXiv preprint arXiv:2507.00363.

[7] Xie, Y., Ren, X., Qi, Y., Hu, Y., & Shan, L. (2025). RecLLM-R1: A two-stage training paradigm with reinforcement learning and chain-of-thought v1. arXiv preprint arXiv:2506.19235.

[8] Luo, H., Wu, B., Jia, H., Zhu, Q., & Shan, L. (2025). LLM-CoT enhanced graph neural recommendation with harmonized group policy optimization. arXiv preprint arXiv:2505.12396.

[9] Meng, W., Shan, L., Ma, S., Liu, D., & Hu, B. (2025). DLNet: A dual-level network with self-and cross-attention for high-resolution remote sensing segmentation. Remote Sensing, 17(7), 1119. https://doi.org/10.3390/rs17071119

[10] Du, B., Shan, L., Shao, X., Zhang, D., Wang, X., & Wu, J. (2025). Transform dual-branch attention net: Efficient semantic segmentation of ultra-high-resolution remote sensing images. Remote Sensing, 17(3), 540. https://doi.org/10.3390/rs17030540

[11] Li, M., Shan, L., Li, X., Bai, Y., Zhou, D., Wang, W., & Chen, S. B. (2021, January). Global-local attention network for semantic segmentation in aerial images. In 2020 25th International Conference on Pattern Recognition (ICPR) (pp. 5704–5711). IEEE. https://doi.org/10.1109/ICPR48806.2021.9412146

[12] Yi, C., & Shan, L. (2025). A global-local cross-attention network for ultra-high resolution remote sensing image semantic segmentation. arXiv preprint arXiv:2506.19406.

[13] Chen, H., Feng, L., Wu, W., Zhu, X., Shan, L., & Hu, K. (2025). F2Net: A frequency-fused network for ultra-high resolution remote sensing segmentation. arXiv preprint arXiv:2506.07847.

[14] Zhang, J. (2025). Asymmetric Mamba-CNN collaborative architecture for large-size remote sensing image semantic segmentation. IEEE Transactions on Geoscience and Remote Sensing.

[15] Ji, Y., & Shan, L. (2024, July). LDNET: Semantic segmentation of high-resolution images via learnable patch proposal and dynamic refinement. In 2024 IEEE International Conference on Multimedia and Expo (ICME) (pp. 1–6). IEEE. https://doi.org/10.1109/ICME57554.2024.10687334

[16] Zhao, L. S. W. Z. G. (2024). Boosting general trimap-free matting in the real-world image. arXiv preprint arXiv:2405.17916.

[17] Shan, L., Wang, W., Lv, K., & Luo, B. (2024). Edge-guided and class-balanced active learning for semantic segmentation of aerial images. arXiv preprint arXiv:2405.18078.

[18] Shan, L., Zhao, G., Xie, J., Cheng, P., Li, X., & Wang, Z. (2023). A data-related patch proposal for semantic segmentation of aerial images. IEEE Geoscience and Remote Sensing Letters, 20, 1–5. https://doi.org/10.1109/LGRS.2023.3286028

[19] Zhao, G., Shan, L., & Wang, W. (2023, September). End-to-end remote sensing change detection of unregistered bi-temporal images for natural disasters. In International Conference on Artificial Neural Networks (pp. 259–270). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-44207-0_22

[20] Shan, L., Wang, W., Lv, K., & Luo, B. (2023). Boosting semantic segmentation of aerial images via decoupled and multilevel compaction and dispersion. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–16. https://doi.org/10.1109/TGRS.2023.3292418

[21] Shan, L., & Wang, W. (2022, May). Mbnet: A multi-resolution branch network for semantic segmentation of ultra-high resolution images. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 2589–2593). IEEE. https://doi.org/10.1109/ICASSP43922.2022.9746130

[22] Shan, L., & Wang, W. (2022). DenseNet-based land cover classification network with deep fusion. IEEE Geoscience and Remote Sensing Letters, 19, 1–5. https://doi.org/10.1109/LGRS.2021.3124015

[23] Shan, L., Li, M., Li, X., Bai, Y., Lv, K., Luo, B., & Wang, W. (2021, January). Uhrsnet: A semantic segmentation network specifically for ultra-high-resolution images. In 2020 25th International Conference on Pattern Recognition (ICPR) (pp. 1460–1466). IEEE. https://doi.org/10.1109/ICPR48806.2021.9412440

[24] Li, M., Shan, L., Wang, W., & et al. (2025). Building lightweight semantic segmentation models for aerial images using dual relation distillation. arXiv preprint arXiv:2506.20688.

[25] Li, M., Shan, L., Wang, W., Lv, K., Luo, B., & Chen, S. B. (2025). Building lightweight semantic segmentation models for aerial images using dual relation distillation. arXiv preprint arXiv:2506.20688.

[26] Yi, E., & Shawn, L. (2025). FlexDataset: Crafting annotated dataset generation for diverse applications. Proceedings of the AAAI Conference on Artificial Intelligence, 39(9). https://doi.org/10.1609/aaai.v39i9.32917

[27] Shan, L., Zhou, W., Li, W., & Ding, X. (2024). Organizing background to explore latent classes for incremental few-shot semantic segmentation. arXiv preprint arXiv:2405.19568.

[28] Shan, L., Zhou, W., Li, W., & Ding, X. (2024). Lifelong learning and selective forgetting via contrastive strategy. arXiv preprint arXiv:2405.18663.

[29] Ding, X., Shan, L., Zhao, G., Wu, M., Zhou, W., & Li, W. (2024). The binary quantized neural network for dense prediction via specially designed upsampling and attention. arXiv preprint arXiv:2405.17776.

[30] Wu, W., Zhao, Y., Li, Z., Shan, L., Zhou, H., & Shou, M. Z. (2024). Continual learning for image segmentation with dynamic query. IEEE Transactions on Circuits and Systems for Video Technology, 34(6), 4874–4886. https://doi.org/10.1109/TCSVT.2023.3326721

[31] Shan, L., Zhou, W., & Zhao, G. (2023, October). Incremental few shot semantic segmentation via class-agnostic mask proposal and language-driven classifier. In Proceedings of the 31st ACM International Conference on Multimedia (pp. 8561–8570). https://doi.org/10.1145/3581783.3612132

[32] Shan, L., Wang, W., Lv, K., & Luo, B. (2022). Class-incremental semantic segmentation of aerial images via pixel-level feature generation and task-wise distillation. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–17. https://doi.org/10.1109/TGRS.2022.3141434

[33] Shan, L., Wang, W., Lv, K., & Luo, B. (2022). Class-incremental learning for semantic segmentation in aerial imagery via distillation in all aspects. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–12. https://doi.org/10.1109/TGRS.2021.3137774

[34] Li, X., Shan, L., & Wang, W. (2021, June). Fusing multitask models by recursive least squares. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 3640–3644). IEEE. https://doi.org/10.1109/ICASSP39728.2021.9414772

[35] Shan, L., Li, X., & Wang, W. (2021, June). Decouple the high-frequency and low-frequency information of images for semantic segmentation. In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1805–1809). IEEE. https://doi.org/10.1109/ICASSP39728.2021.9414704

[36] Li, X., Shan, L., Li, M., & Wang, W. (2021, January). Energy minimum regularization in continual learning. In 2020 25th International Conference on Pattern Recognition (ICPR) (pp. 6404–6409). IEEE. https://doi.org/10.1109/ICPR48806.2021.9413217.