PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decoding

Xiang Liu, Jinxiang Wang, Bin Chen, Zimo Liu, Mingyao Hong, Jiawei Li, Yaowei Wang, Shu-Tao Xia

Keywords: Implicit Neural Representation, Image Compression

TL;DR: An INR-based image codec capable of encoding at 20 FPS and decoding at 2000 FPS.

Abstract: Implicit neural representation (INR) has achieved remarkable progress in novel view synthesis and image/video coding in recent years. Compared to end-to-end image codecs, INR-based image compressors demonstrate significant advantages in decoding complexity. However, their practical application has been hindered by the inferior encoding speed. Compared to conventional end-to-end codecs, INR-based compressors enjoy markedly lower decoding complexity, yet their adoption in practice remains limited due to slow encoding and underutilized decoding efficiency. In this work, we propose an end-to-end INR image coding architecture, **P**ractical **I**NR Image **C**odec (PIC), that computes all the necessary information for INR network in a single forward pass, achieving an encoding speed of 20 FPS. Additionally, we implement a highly optimized decoder that reaches 2000 FPS decoding speed, significantly surpassing JPEG's performance at comparable rate-distortion (RD) performance. To the best of our knowledge, this work presents the first learning-based image codec that simultaneously outperforms or is comparable with JPEG in both RD performance and decoding speed while maintaining practical encoding speed. Code will be released.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 4372