arXiv Open Access 2022

Opening the Black Box of Learned Image Coders

Zhihao Duan Ming Lu Zhan Ma Fengqing Zhu

Lihat Sumber

Abstrak

End-to-end learned lossy image coders (LICs), as opposed to hand-crafted image codecs, have shown increasing superiority in terms of the rate-distortion performance. However, they are mainly treated as black-box systems and their interpretability is not well studied. In this paper, we show that LICs learn a set of basis functions to transform input image for its compact representation in the latent space, as analogous to the orthogonal transforms used in image coding standards. Our analysis provides insights to help understand how learned image coders work and could benefit future design and development.

Topik & Kata Kunci

eess.IV

Penulis (4)

Zhihao Duan

Ming Lu

Zhan Ma

Fengqing Zhu

Format Sitasi

APA MLA BibTeX

Duan, Z., Lu, M., Ma, Z., Zhu, F. (2022). Opening the Black Box of Learned Image Coders. https://arxiv.org/abs/2202.13209

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2022
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓