T-MLP: Tailed Multi-Layer Perceptron for Level-of-Detail Signal Representation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Chuanxiang, Zhou, Yuanfeng, Wei, Guangshun, Ren, Siyu, Liu, Yuan, Hou, Junhui, Wang, Wenping
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914063810822144
author Yang, Chuanxiang
Zhou, Yuanfeng
Wei, Guangshun
Ren, Siyu
Liu, Yuan
Hou, Junhui
Wang, Wenping
author_facet Yang, Chuanxiang
Zhou, Yuanfeng
Wei, Guangshun
Ren, Siyu
Liu, Yuan
Hou, Junhui
Wang, Wenping
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00066
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle T-MLP: Tailed Multi-Layer Perceptron for Level-of-Detail Signal Representation
Yang, Chuanxiang
Zhou, Yuanfeng
Wei, Guangshun
Ren, Siyu
Liu, Yuan
Hou, Junhui
Wang, Wenping
Machine Learning
Graphics
Image and Video Processing
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.
title T-MLP: Tailed Multi-Layer Perceptron for Level-of-Detail Signal Representation
topic Machine Learning
Graphics
Image and Video Processing
url https://arxiv.org/abs/2509.00066