Barreiro, AlbertMarí, RogerRedondo, RafaelHaro Ortega, GloriaBosch, CarlesBerga, David2025-04-012025-04-012025Barreiro A, Marí R, Redondo R, Haro G, Bosch C, Berga D. Specularity in NeRFs: a comparative study of Ref-NeRF and NRFF. Image Processing On Line. 2024;15:22-44. DOI: 10.5201/ipol.2025.5622015-1232http://hdl.handle.net/10230/70064Neural Radiance Fields (NeRF) have emerged as a leading technology for 3D digitization, especially for their high accuracy and intricate detailing. Despite their advancements, early NeRF models struggle to handle reflections on specular surfaces effectively. To address this, alternative approaches such as Ref-NeRF and NRFF were proposed to improve fidelity in representing this physical phenomenon. This study compares these two models, providing an analysis of their effectiveness and limitations in dealing with complex specularities. We demonstrate that both methods struggle with inter-reflections and tend to model anisotropic specularities by altering the predicted surface normals.application/pdfeng© 2025 IPOL & the authors CC–BY–NC–SA This article is available online with supplementary materials, software, datasets and online demo at https://doi.org/10.5201/ipol.2025.562.info:eu-repo/semantics/articlehttp://dx.doi.org/10.5201/ipol.2025.5623D reconstructionView synthesisPhotorealistic renderingVolume renderingNeural radiance fieldsinfo:eu-repo/semantics/openAccess