I-INR: Iterative Implicit Neural Representations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908996137385984 |
|---|---|
| author | Haider, Ali Ali, Muhammad Salman Qamar, Maryam Khalil, Tahir Kim, Soo Ye Oh, Jihyong Tartaglione, Enzo Bae, Sung-Ho |
| author_facet | Haider, Ali Ali, Muhammad Salman Qamar, Maryam Khalil, Tahir Kim, Soo Ye Oh, Jihyong Tartaglione, Enzo Bae, Sung-Ho |
| contents | Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural networks. However, INRs are prone to the spectral bias problem, limiting their ability to retain high-frequency information, and often struggle with noise robustness. Motivated by recent trends in iterative refinement processes, we propose Iterative Implicit Neural Representations (I-INRs). This novel plug-and-play framework iteratively refines signal reconstructions to restore high-frequency details, improve noise robustness, and enhance generalization, ultimately delivering superior reconstruction quality. I-INRs integrate seamlessly into existing INR architectures with only a 0.5-2% increase in parameters. During reconstruction, the iterative refinement adds just 0.8-1.6% additional FLOPs over the baseline while delivering a substantial performance boost of up to +2.0 PSNR. Extensive experiments demonstrate that I-INRs consistently outperform WIRE, SIREN, and Gauss across various computer vision tasks, including image fitting, image denoising, and object occupancy prediction. The code is available at github.com/optimizer077/I-INR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17364 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | I-INR: Iterative Implicit Neural Representations Haider, Ali Ali, Muhammad Salman Qamar, Maryam Khalil, Tahir Kim, Soo Ye Oh, Jihyong Tartaglione, Enzo Bae, Sung-Ho Computer Vision and Pattern Recognition Implicit Neural Representations (INRs) have revolutionized signal processing and computer vision by modeling signals as continuous, differentiable functions parameterized by neural networks. However, INRs are prone to the spectral bias problem, limiting their ability to retain high-frequency information, and often struggle with noise robustness. Motivated by recent trends in iterative refinement processes, we propose Iterative Implicit Neural Representations (I-INRs). This novel plug-and-play framework iteratively refines signal reconstructions to restore high-frequency details, improve noise robustness, and enhance generalization, ultimately delivering superior reconstruction quality. I-INRs integrate seamlessly into existing INR architectures with only a 0.5-2% increase in parameters. During reconstruction, the iterative refinement adds just 0.8-1.6% additional FLOPs over the baseline while delivering a substantial performance boost of up to +2.0 PSNR. Extensive experiments demonstrate that I-INRs consistently outperform WIRE, SIREN, and Gauss across various computer vision tasks, including image fitting, image denoising, and object occupancy prediction. The code is available at github.com/optimizer077/I-INR. |
| title | I-INR: Iterative Implicit Neural Representations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.17364 |