Abstract
Relightable images created from Multi-Light Image Collections (MLICs) are among the most employed models for
interactive object exploration in cultural heritage (CH). In recent years, neural representations have been
shown to produce higher-quality images at similar storage costs to the more classic analytical models such
as Polynomial Texture Maps (PTM) or Hemispherical Harmonics (HSH). However, the Neural RTI models proposed
in the literature perform the image relighting with decoder networks with a high number of parameters,
making decoding slower than for classical methods. Despite recent efforts targeting model reduction and
multi-resolution adaptive rendering, exploring high-resolution images, especially on high-pixel-count
displays, still requires significant resources and is only achievable through progressive rendering in
typical setups. In this work, we show how, by using knowledge distillation from an original (teacher) Neural
RTI network, it is possible to create a more efficient RTI decoder (student network). We evaluated the
performance of the network compression approach on existing RTI relighting benchmarks, including both
synthetic and real datasets, and on novel acquisitions of high-resolution images. Experimental results show
that we can keep the student prediction close to the teacher with up to 80% parameter reduction and almost
ten times faster rendering when embedded in an online viewer.
