Level-of-detail (LoD) representation is critical for efficiently modeling and transmitting various types of signals, such as images and 3D shapes. In this work, we propose a novel network architecture that enables LoD signal representation. Our approach builds on a modified Multi-Layer Perceptron (MLP), which inherently operates at a single scale and thus lacks native LoD support. Specifically, we introduce the Tailed Multi-Layer Perceptron (T-MLP), which extends the MLP by attaching an output branch, also called tail, to each hidden layer. Each tail refines the residual between the current prediction and the ground-truth signal, so that the accumulated outputs across layers correspond to the target signals at different LoDs, enabling multi-scale modeling with supervision from only a single-resolution signal. Extensive experiments demonstrate that our T-MLP outperforms existing neural LoD baselines across diverse signal representation tasks.
@article{arxiv.2509.00066,
title = {T-MLP: Tailed Multi-Layer Perceptron for Level-of-Detail Signal Representation},
author = {Chuanxiang Yang and Yuanfeng Zhou and Guangshun Wei and Siyu Ren and Yuan Liu and Junhui Hou and Wenping Wang},
journal= {arXiv preprint arXiv:2509.00066},
year = {2025}
}