Publications

Authors:

Dulecha, TINSAE GEBRECHRISTOS; Righetto, Leonardo; Pintus, Ruggero; Gobbetti, Enrico; Giachetti, Andrea

Title:

Disk-NeuralRTI: Optimized NeuralRTI Relighting through Knowledge Distillation

Year:

2024

Type of item:

Contributo in atti di convegno

Tipologia ANVUR:

Contributo in Atti di convegno

Language:

Inglese

Congresso:

Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference

Place:

Verona

Period:

14 - 15 November 2024

Publisher:

Eurographics

ISBN:

978-3-03868-265-3

Page numbers:

1-10

Keyword:

Reflectance Transformation Imaging, Neural Networks, Knowledge Distillation

Short description of contents:

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 higherquality 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-pixelcount 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.

Web page:

https://diglib.eg.org/items/d4b19fb8-bc5c-4bc6-8839-a76b2c353cb4

Product ID:

145825

Handle IRIS:

11562/1162371

Last Modified:

May 30, 2025

Bibliographic citation:

Dulecha, TINSAE GEBRECHRISTOS; Righetto, Leonardo; Pintus, Ruggero; Gobbetti, Enrico; Giachetti, Andrea, Disk-NeuralRTI: Optimized NeuralRTI Relighting through Knowledge Distillation  in Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference , Eurographics , Proceedings of "Smart Tools and Applications in Graphics - Eurographics Italian Chapter Conference" , Verona , 14 - 15 November 2024 , 2024 , pp. 1-10

Consulta la scheda completa presente nel repository istituzionale della Ricerca di Ateneo