用超网络统一生成纹理编码和解码器，实现快速实时渲染。
Neural Texture Compression using Hypernetworks
- 训练超网络直接输出隐变量和MLP权重，免去每材质优化
- 在相同质量下比现有方法更快，支持多解码器并行生成
- 可扩展至超分辨率纹理重建，适合游戏与实时渲染场景
近期神经纹理压缩工作表明，可通过小规模的材料专属表示（包括隐式纹理和小型多层感知机解码器）实现实时着色下的物理渲染。但现有方法需针对每个材质对MLP和隐变量配置进行梯度下降优化。本文提出训练单一超网络，直接输出隐式特征及MLP的权重与偏置。尽管解空间高维，该方法仍可达到当前最优神经纹理压缩器的相近质量。进一步地，该方法可同时推断多个解码器，甚至生成支持超分辨率重建的解码器。
原文摘要 · Abstract (English)
Recent work on neural texture compression has demonstrated that it is possible to learn small, per-material texture representations (composed of latent textures and a small Multi-Layer Perceptron decoder) that can be decoded in real-time during shading to reproduce the input to a physically based shading model. However, existing methods require performing gradient-descent optimization per material for a given MLP and latent configuration. In this work, we train a single hypernetwork that outputs both the latent features and the MLP's weights and biases. Though the solution space is high-dimensional, this approach produces results comparable in quality to the current reference neural texture compressors. We further extend this approach to infer multiple decoders at once or even produce decoders that learn super-resolution.
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。