2000 character limit reached
TRIDENT: The Nonlinear Trilogy for Implicit Neural Representations
Published 21 Nov 2023 in cs.CV and eess.IV | (2311.13610v1)
Abstract: Implicit neural representations (INRs) have garnered significant interest recently for their ability to model complex, high-dimensional data without explicit parameterisation. In this work, we introduce TRIDENT, a novel function for implicit neural representations characterised by a trilogy of nonlinearities. Firstly, it is designed to represent high-order features through order compactness. Secondly, TRIDENT efficiently captures frequency information, a feature called frequency compactness. Thirdly, it has the capability to represent signals or images such that most of its energy is concentrated in a limited spatial region, denoting spatial compactness. We demonstrated through extensive experiments on various inverse problems that our proposed function outperforms existing implicit neural representation functions.
- Ntire 2017 challenge on single image super-resolution: Dataset and study. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 126–135, 2017.
- Solving inverse problems using data-driven models. Acta Numerica, 28:1–174, 2019.
- Introduction to inverse problems in imaging. CRC press, 2021.
- Low-complexity single-image super-resolution based on nonnegative neighbor embedding. 2012.
- Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information. IEEE Transactions on information theory, 52(2):489–509, 2006.
- The cancer imaging archive (tcia): maintaining and operating a public information repository. Journal of digital imaging, 26:1045–1057, 2013.
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Communications on Pure and Applied Mathematics: A Journal Issued by the Courant Institute of Mathematical Sciences, 57(11):1413–1457, 2004.
- Anthony J Devaney. Mathematical foundations of imaging, tomography and wavefield inversion. Cambridge University Press, 2012.
- Regularization of inverse problems. Springer Science & Business Media, 1996.
- Multiplicative filter networks. In International Conference on Learning Representations, 2020.
- Implicit neural representations with levels-of-experts. Advances in Neural Information Processing Systems, 35:2564–2576, 2022.
- Sparsity regularization for parameter identification problems. Inverse Problems, 28(12):123001, 2012.
- Statistical inverse problems: discretization, model reduction and inverse crimes. Journal of computational and applied mathematics, 198(2):493–504, 2007.
- Neuralgrasps: Learning implicit representations for grasps of multiple robotic hands. In Conference on Robot Learning, pages 516–526. PMLR, 2023.
- A method for stochastic optimization. In International conference on learning representations (ICLR), page 6. San Diego, California;, 2015.
- Andreas Kirsch et al. An introduction to the mathematical theory of inverse problems. Springer, 2011.
- Using deep neural networks for inverse problems in imaging: beyond analytical methods. IEEE Signal Processing Magazine, 35(1):20–36, 2018.
- Convolutional neural networks for inverse problems in imaging: A review. IEEE Signal Processing Magazine, 34(6):85–95, 2017.
- Occupancy networks: Learning 3d reconstruction in function space. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4460–4470, 2019.
- Nerf: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM, 65(1):99–106, 2021.
- Linear and nonlinear inverse problems with practical applications. SIAM, 2012.
- Instant neural graphics primitives with a multiresolution hash encoding. ACM Transactions on Graphics (ToG), 41(4):1–15, 2022.
- Deep learning techniques for inverse problems in imaging. IEEE Journal on Selected Areas in Information Theory, 1(1):39–56, 2020.
- Beyond periodicity: Towards a unifying framework for activations in coordinate-mlps. In European Conference on Computer Vision, pages 142–158. Springer, 2022.
- Nonlinear total variation based noise removal algorithms. Physica D: nonlinear phenomena, 60(1-4):259–268, 1992.
- Wire: Wavelet implicit neural representations, 2023.
- Implicit neural representations with periodic activation functions, 2020.
- Fourier features let networks learn high frequency functions in low dimensional domains, 2020.
- Plug-and-play priors for model based reconstruction. In 2013 IEEE global conference on signal and information processing, pages 945–948. IEEE, 2013.
- Curtis R Vogel. Computational methods for inverse problems. SIAM, 2002.
- Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4):600–612, 2004.
- Tfpnp: Tuning-free plug-and-play proximal algorithms with applications to inverse imaging problems. The Journal of Machine Learning Research, 23(1):699–746, 2022.
- A structured dictionary perspective on implicit neural representations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 19228–19238, 2022.
- On single image scale-up using sparse-representations. In Curves and Surfaces: 7th International Conference, Avignon, France, June 24-30, 2010, Revised Selected Papers 7, pages 711–730. Springer, 2012.
- Homeomorphic image registration via conformal-invariant hyperelastic regularisation. arXiv preprint arXiv:2303.08113, 2023.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
