Work

Learn How to Prune Pixels for Multi-View Neural Image-Based Synthesis

Year: 2023

Type: conference-paper

Abstract: Image-based rendering techniques stand at the core of an immersive experience for the user, as they generate novel views given a set of multiple input images. Since they have shown good performance in terms of objective and subjective quality, the research community devotes great effort to their improvement. However, the large volume of data necessary to render at the receiver's side hinders applications in limited bandwidth environments or prevents their employment in real-time applications. We present LeHoPP, a method for input pixel pruning, where we examine the importance of each input pixel concerning the rendered view, and we avoid the use of irrelevant pixels. Even without retraining the image-based rendering network, our approach shows a good tradeoff between synthesis quality and pixel rate. When tested in the general neural rendering framework, compared to other pruning baselines, LeHoPP gains between 0.9 dB and 3.6 dB on average.

Source: IEEE International Conference on Multimedia and Expo workshops

DOI: 10.1109/icmew59549.2023.00034

Authors: Marta Milovanović, Enzo Tartaglione, Marco Cagnazzo, Félix Henry

Institutions: Institut Polytechnique de Paris, Laboratoire Traitement et Communication de l’Information, Orange (France)

Language: English

Topic: Image and Video Quality Assessment

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: European Commission

Award: G2233891588