Scholarlink

COIN++ is a special variant of Implicit Neural Representation (INR), which encodes signals as modulations applied to the base INR network. It is becoming a promising method for applications in image compression. However, INR’s effectiveness is hindered by its inability to capture high-frequency details in the image representation. We propose a novel COIN++ framework using Chebyshev approximation to enhance high-frequency signal learning and image compression. In addition, we design an adaptable image partitioning technology and an integrated quantization method to further the image compression performance of COIN++ in the framework. Experiments demonstrate our framework significantly enhances both representational capacity and compression rate compared to the COIN++ baseline, with notable PSNR improvements.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CPE COIN++: Towards Optimized Implicit Neural Representation Compression Via Chebyshev Positional Encoding

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Haocheng Chu,
  • Shaohui Dai,
  • Wenqi Ding,
  • Xin Shi,
  • Tianshuo Xu,
  • Pingyang Dai,
  • Shengchuan Zhang,
  • Yan Zhang,
  • Xiang Chang,
  • Chih-Min Lin,
  • Fei Chao,
  • Changjiang Shang,
  • Qiang Shen

摘要

COIN++ is a special variant of Implicit Neural Representation (INR), which encodes signals as modulations applied to the base INR network. It is becoming a promising method for applications in image compression. However, INR’s effectiveness is hindered by its inability to capture high-frequency details in the image representation. We propose a novel COIN++ framework using Chebyshev approximation to enhance high-frequency signal learning and image compression. In addition, we design an adaptable image partitioning technology and an integrated quantization method to further the image compression performance of COIN++ in the framework. Experiments demonstrate our framework significantly enhances both representational capacity and compression rate compared to the COIN++ baseline, with notable PSNR improvements.