Specularity in NeRFs: a comparative study of Ref-NeRF and NRFF

Neural 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 s...

Descripción completa

Detalles Bibliográficos
Autores: Barreiro, Albert, Marí, Roger, Redondo, Rafael, Haro Ortega, Gloria, Bosch, Carles, Berga, David
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2025
País:España
Institución:Universitat Pompeu Fabra
Repositorio:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/70064
Acceso en línea:http://hdl.handle.net/10230/70064
http://dx.doi.org/10.5201/ipol.2025.562
Access Level:acceso abierto
Palabra clave:3D reconstruction
View synthesis
Photorealistic rendering
Volume rendering
Neural radiance fields
Descripción
Sumario:Neural 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.