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

Xiang Liu, Jinxiang Wang, Bin Chen, Zimo Liu, Mingyao Hong +3 more
9/8/2026
cs.CV

Official code: actcwlf/PIC (0 stars, MIT, last commit 2026-06-22).

Abstract

Implicit neural representation (INR) has achieved remarkable progress in novel view synthesis and image/video coding in recent years.Compared to conventional end-to-end image codecs, INR-based compressors demonstrate significant advantages in decoding complexity. However, their practical application has been hindered by the inferior encoding speed and underutilized decoding efficiency.In this work, we propose a feedforward INR image coding architecture, Practical INR Image Codec (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 is available at https://github.com/actcwlf/PIC.

View on arXivView PDF

Code Implementations(1)

actcwlf/PICOfficial100%
MIT

PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decoding (ECCV2026)

00Jun 22, 20264 months agoMIT

Similar Papers

C3: High-Performance and Low-Complexity Neural Compression from a Single Image or Video

89% match2023

NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation

87% match2024

NeRV: Neural Representations for Videos

87% match1 repo3272021

Computationally-Efficient Neural Image Compression with Shallow Decoders

86% match1 repo352023

CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis

86% match1 repo312024

Joint Hierarchical Priors and Adaptive Spatial Resolution for Efficient Neural Image Compression

86% match2023

Cite this paper

@article{liu2026pic,
  title  = {PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decoding},
  author = {Xiang Liu and Jinxiang Wang and Bin Chen and Zimo Liu and Mingyao Hong and Jiawei Li and Yaowei Wang and Shu-tao Xia},
  year   = {2026},
  eprint = {2609.09020},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2609.09020v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2609.09020.svg)](https://codeofpaper.com/paper/2609.09020)

Discussion