{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T18:19:40Z","timestamp":1785435580852,"version":"3.56.0"},"reference-count":25,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T00:00:00Z","timestamp":1782000000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100022866","name":"Mutah University","doi-asserted-by":"crossref","award":["2025\/1051"],"award-info":[{"award-number":["2025\/1051"]}],"id":[{"id":"10.13039\/100022866","id-type":"DOI","asserted-by":"crossref"}]},{"award":["2025\/1051"],"award-info":[{"award-number":["2025\/1051"]}],"id":[{"id":"https:\/\/ror.org\/008g9ns82","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>It is well-known that activation functions are crucial in determining spectral expressiveness, training dynamics, and reconstruction accuracy in implicit neural representations (INRs), which employ coordinate-based multilayer perceptrons to represent continuous signals. Despite showing excellent performance, sinusoidal activations, for example SIREN, are limited in their adaptability to diverse signal types due to their fixed harmonic structure. In this paper, we propose two novel periodic activation functions for INRs. (1) Harmonic generalizes sinusoidal activations by combining the fundamental frequency with learned second and third harmonics through per-neuron trainable amplitude coefficients, resulting in a richer spectral basis within the SIREN initialization framework. (2) PM-FINER (Phase-Modulated FINER) extends the variable-periodic FINER activation by embedding frequency modulation synthesis directly into the instantaneous phase, enabling data-driven phase distortion via a learnable modulation index and carrier ratio. We conducted comprehensive experiments spanning nine architectural configurations (including SIREN, WIRE, FINER, Gaussian, Harmonic, PM-FINER, and an additional direct comparison against the Subtractive Modulative Network (SMN)), using six natural images, three learning rate schedulers, and three random seeds, totaling 486 main training runs (534 runs total including an \u03c90 sensitivity sweep). Our evaluation combined peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and rigorous statistical analysis, such as paired t-tests, Wilcoxon signed-rank tests, Cohen\u2019s d effect sizes, and Friedman rank tests. Under cosine annealing, Harmonic achieves a mean PSNR gain of 6.08 dB over SIREN and 2.57 dB over FINER (both p&lt;0.001, Cohen\u2019s d&gt;3.7), while PM-FINER ranks statistically on par with Harmonic (mean difference 0.17 dB, p=0.36), outperforming all of the other baselines. Compared with SMN, Harmonic outperforms it by +7.94 dB under cosine annealing (Bonferroni-adjusted p&lt;10\u22125, Cohen\u2019s d=12.3), winning on all six images. Additionally, the Friedman ranking across the six images confirmed Harmonic (with mean rank =1.33) and PM-FINER (with mean rank =1.67), being the top two methods under cosine annealing. Our results establish interpretable multi-harmonic and phase-modulated activations as real alternatives to the existing INR activation functions.<\/jats:p>","DOI":"10.3390\/make8060170","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T09:49:55Z","timestamp":1782121795000},"page":"170","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Harmonic and Phase-Modulated Activation Functions for Implicit Neural Representations: A Comprehensive Benchmark Study"],"prefix":"10.3390","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3555-8501","authenticated-orcid":false,"given":"Ahmad S.","family":"Tarawneh","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, Mutah University, Al-Karak 61710, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omar","family":"Lasassmeh","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Mutah University, Al-Karak 61710, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anas A.","family":"Alkasasbeh","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Mutah University, Al-Karak 61710, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3658-1284","authenticated-orcid":false,"given":"Abdulkareem","family":"Alzahrani","sequence":"additional","affiliation":[{"name":"Faculty of Computing and Information, Al-Baha University, Al-Baha 65779, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0813-142X","authenticated-orcid":false,"given":"Khalid","family":"Almohammadi","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of Tabuk, Tabuk 71491, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8378-3546","authenticated-orcid":false,"given":"Maha","family":"Alamri","sequence":"additional","affiliation":[{"name":"Faculty of Computing and Information, Al-Baha University, Al-Baha 65779, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9991-304X","authenticated-orcid":false,"given":"Ahmad B.","family":"Hassanat","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Mutah University, Al-Karak 61710, Jordan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,21]]},"reference":[{"key":"ref_1","first-page":"7462","article-title":"Implicit Neural Representations with Periodic Activation Functions","volume":"Volume 33","author":"Sitzmann","year":"2020","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., and Ng, R. (2020). NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., and Lovegrove, S. (2019). DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., and Geiger, A. (2019). Occupancy Networks: Learning 3D Reconstruction in Function Space. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Computer Vision Foundation.","DOI":"10.1109\/CVPR.2019.00459"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1016\/j.jcp.2018.10.045","article-title":"Physics-Informed Neural Networks","volume":"378","author":"Raissi","year":"2019","journal-title":"J. Comput. Phys."},{"key":"ref_6","unstructured":"Dupont, E., Goli\u0144ski, A., Alizadeh, M., Teh, Y.W., and Doucet, A. (2021). COIN: COmpression with Implicit Neural Representations. Proceedings of the Neural Compression Workshop at ICLR, OpenReview.net."},{"key":"ref_7","unstructured":"Rahaman, N., Baratin, A., Arpit, D., Draxler, F., Lin, M., Hamprecht, F.A., Bengio, Y., and Courville, A. (2019). On the Spectral Bias of Neural Networks. Proceedings of the 36th International Conference on Machine Learning, PMLR."},{"key":"ref_8","first-page":"7537","article-title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","volume":"Volume 33","author":"Tancik","year":"2020","journal-title":"Proceedings of the Advances in Neural Information Processing Systems"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Saragadam, V., LeJeune, D., Tan, J., Balakrishnan, G., Veeraraghavan, A., and Baraniuk, R.G. (2023). WIRE: Wavelet Implicit Neural Representations. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Computer Vision Foundation.","DOI":"10.1109\/CVPR52729.2023.01775"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ramasinghe, S., and Lucey, S. (2022). Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-19827-4_9"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Liu, M., Zeng, J., Chen, M., Liu, J., Che, J., Dai, Z., Xu, W., Cai, D., and Chen, J. (2024). FINER: Flexible Spectral-bias Tuning in Implicit Neural Representation by Variable-periodic Activation Functions. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Computer Vision Foundation.","DOI":"10.1109\/CVPR52733.2024.00262"},{"key":"ref_12","unstructured":"Zhu, H., Fang, L., and Loy, C.C. (2024). FINER++: Building a Family of Variable-periodicity Functions for Activation in Implicit Neural Representation. arXiv."},{"key":"ref_13","unstructured":"Morsali, A., Sadeghi, M., and Babaie-Zadeh, M. (2025). STAF: Sinusoidal Trainable Activation Functions for Implicit Neural Representations. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, T., Yang, Z., Flierl, M., Salzmann, M., and S\u00fcsstrunk, S. (2026). Subtractive Modulative Network with Learnable Periodic Activations. arXiv.","DOI":"10.1109\/ICASSP55912.2026.11461478"},{"key":"ref_15","unstructured":"Heidari, M., Rezaeian, R., Azad, R., Merhof, D., Soltanian-Zadeh, H., and Hacihaliloglu, I. (2024). SL2A-INR: Single-Layer Learnable Activation for Implicit Neural Representation. arXiv."},{"key":"ref_16","unstructured":"Alsakabi, M., Mobeirek, W., Dolan, J.M., and Tonguz, O.K. (2025). FM-SIREN & FM-FINER: Implicit Neural Representation Using Nyquist-based Orthogonality. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image Quality Assessment: From Error Visibility to Structural Similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_18","unstructured":"(2024). H-SIREN: Improving Implicit Neural Representations with Hyperbolic Sine Activation. arXiv."},{"key":"ref_19","first-page":"526","article-title":"The Synthesis of Complex Audio Spectra by Means of Frequency Modulation","volume":"21","author":"Chowning","year":"1973","journal-title":"J. Audio Eng. Soc."},{"key":"ref_20","unstructured":"(2026, June 11). Kodak Lossless True Color Image Suite. Available online: http:\/\/r0k.us\/graphics\/kodak\/."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"e453","DOI":"10.7717\/peerj.453","article-title":"scikit-image: Image processing in Python","volume":"2","author":"Boulogne","year":"2014","journal-title":"PeerJ"},{"key":"ref_22","unstructured":"Kingma, D.P., and Ba, J. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_23","unstructured":"Loshchilov, I., and Hutter, F. (2017, January 24\u201326). SGDR: Stochastic Gradient Descent with Warm Restarts. Proceedings of the 5th International Conference on Learning Representations, Toulon, France."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Hassanat, A.B., Alqaralleh, M.K., Tarawneh, A.S., Almohammadi, K., Alamri, M., Alzahrani, A., Altarawneh, G.A., and Alhalaseh, R. (2024). A Novel Outlier-Robust Accuracy Measure for Machine Learning Regression Using a Non-Convex Distance Metric. Mathematics, 12.","DOI":"10.21203\/rs.3.rs-4492948\/v1"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tarawneh, A.S. (2026). HasLoss: A novel Hassanat distance-based loss functions for binary classification. Front. Artif. Intell., 8.","DOI":"10.3389\/frai.2025.1690830"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/6\/170\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T04:25:03Z","timestamp":1782534303000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/8\/6\/170"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,21]]},"references-count":25,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["make8060170"],"URL":"https:\/\/doi.org\/10.3390\/make8060170","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,21]]}}}