通过分位面分解实现高精度隐式神经表示的无损压缩
Towards Lossless Implicit Neural Representation via Bit Plane Decomposition
- 将隐式神经表示分解为逐位面预测，降低模型规模上限
- 在16位深度图像与音频上实现无损重建，首次突破精度瓶颈
- 适合需要高保真重建的图像压缩与极低精度量化场景
我们从数字视角量化了隐式神经表示（INR）模型大小的理论上限，发现所需位精度越高，模型规模上限呈指数增长。为此，本文提出位平面分解方法，使INR逐位面进行预测，等效降低了模型规模上限。验证了降低上限可加速收敛且保持模型大小不变。该方法在2D图像与音频拟合任务中实现了无损重建，包括16位高比特深度信号，此前难以实现。首次揭示了位偏置现象，即INR优先学习最高有效位（MSB）。拓展了INR应用至位深度扩展、无损图像压缩与极端网络量化。源代码已开源：https://github.com/WooKyoungHan/LosslessINR。
原文摘要 · Abstract (English)
We quantify the upper bound on the size of the implicit neural representation (INR) model from a digital perspective. The upper bound of the model size increases exponentially as the required bit-precision increases. To this end, we present a bit-plane decomposition method that makes INR predict bit-planes, producing the same effect as reducing the upper bound of the model size. We validate our hypothesis that reducing the upper bound leads to faster convergence with constant model size. Our method achieves lossless representation in 2D image and audio fitting, even for high bit-depth signals, such as 16-bit, which was previously unachievable. We pioneered the presence of bit bias, which INR prioritizes as the most significant bit (MSB). We expand the application of the INR task to bit depth expansion, lossless image compression, and extreme network quantization. Our source code is available at https://github.com/WooKyoungHan/LosslessINR
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。