I-INR: Iterative Implicit Neural Representations

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.

Authors

• Ali Haider Kyung Hee University
• Muhammad Salman Ali Kyung Hee University, Republic of Korea
• Maryam Qamar Kyung Hee University, Republic of Korea
• Tahir Khalil Kyung Hee University, Republic of Korea
• Soo Ye Kim Adobe Research
• Jihyong Oh
• Enzo Tartaglione LTCI, Télécom Paris, Institut Polytechnique de Paris
• Sung-Ho Bae Kyung Hee University

Keywords

No keywords are indexed for this paper.