0616904 20250320140311.720250213235959.9 85216108770 001420733900001 10.1016/j.dsp.2025.105022 14 s. P cav_un_epca*02527191051-2004159Elsevier Demosaicking Implicit neural representation Inverse problems cav_un_auth*0379363 Kerepecký Tomáš UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing CZ K Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101209 Šroubek Filip UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0101087 Flusser Jan UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing Ústav teorie informace a automatizace AV ČR, v. v. i. https://library.utia.cas.cz/separaty/2025/ZOI/kerepecky-0616904.pdf https://www.sciencedirect.com/science/article/pii/S1051200425000442?via%3Dihub GA25-15933S GA ČR cav_un_auth*0483946 We propose a novel approach to enhance image demosaicking algorithms using implicit neural representations (INR). Our method employs a multi-layer perceptron to encode RGB images, combining original Bayer measurements with an initial estimate from existing demosaicking methods to achieve superior reconstructions. A key innovation is the integration of two loss functions: a Bayer loss for fidelity to sensor data and a complementary loss that regularizes reconstruction using interpolated data from the initial estimate. This combination, along with INR’s inherent ability to capture fine details, enables hig-fidelity reconstructions that incorporate information from both sources. Furthermore, we demonstrate that INR can effectively correct artifacts in state-of-the-art demosaicking methods when input data diverge from the training distribution, such as in cases of noise or blur. This adaptability highlights the transformative potential of INR-based demosaicking, offering a robust solution to this challenging problem. 2026 IN WOS 10000 10200 10201 3 RVO:67985556 https://hdl.handle.net/11104/0364269 cav_un_auth*0329918 FJFI ČVUT Praha CZ S 105022 C ENGINEERING.ELECTRICAL&ELECTRONIC 2.9 0.6 4.3 0.00715 0.589 7998 96 0.704 45.4 3.83 4297 Q2 2.600 492 Q2 57.2 0.67 Q2 57.2 2025 85216108770 SCOPUS PUBMED 001420733900001 WOS cav_un_epca*0252719 Digital Signal Processing 159 1 2025 1051-2004 1095-4333 Elsevier