Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yuyang, Xie, Baao, Zhu, Hu, Wang, Qi, Guo, Huanting, Jin, Xin, Zeng, Wenjun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908302865072128
author Zhang, Yuyang
Xie, Baao
Zhu, Hu
Wang, Qi
Guo, Huanting
Jin, Xin
Zeng, Wenjun
author_facet Zhang, Yuyang
Xie, Baao
Zhu, Hu
Wang, Qi
Guo, Huanting
Jin, Xin
Zeng, Wenjun
contents Gaussian Splatting (GS) has recently marked a significant advancement in 3D reconstruction, delivering both rapid rendering and high-quality results. However, existing 3DGS methods pose challenges in understanding underlying 3D semantics, which hinders model controllability and interpretability. To address it, we propose an interpretable single-view 3DGS framework, termed 3DisGS, to discover both coarse- and fine-grained 3D semantics via hierarchical disentangled representation learning (DRL). Specifically, the model employs a dual-branch architecture, consisting of a point cloud initialization branch and a triplane-Gaussian generation branch, to achieve coarse-grained disentanglement by separating 3D geometry and visual appearance features. Subsequently, fine-grained semantic representations within each modality are further discovered through DRL-based encoder-adapters. To our knowledge, this is the first work to achieve unsupervised interpretable 3DGS. Evaluations indicate that our model achieves 3D disentanglement while preserving high-quality and rapid reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2504_04190
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning
Zhang, Yuyang
Xie, Baao
Zhu, Hu
Wang, Qi
Guo, Huanting
Jin, Xin
Zeng, Wenjun
Computer Vision and Pattern Recognition
Gaussian Splatting (GS) has recently marked a significant advancement in 3D reconstruction, delivering both rapid rendering and high-quality results. However, existing 3DGS methods pose challenges in understanding underlying 3D semantics, which hinders model controllability and interpretability. To address it, we propose an interpretable single-view 3DGS framework, termed 3DisGS, to discover both coarse- and fine-grained 3D semantics via hierarchical disentangled representation learning (DRL). Specifically, the model employs a dual-branch architecture, consisting of a point cloud initialization branch and a triplane-Gaussian generation branch, to achieve coarse-grained disentanglement by separating 3D geometry and visual appearance features. Subsequently, fine-grained semantic representations within each modality are further discovered through DRL-based encoder-adapters. To our knowledge, this is the first work to achieve unsupervised interpretable 3DGS. Evaluations indicate that our model achieves 3D disentanglement while preserving high-quality and rapid reconstruction.
title Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.04190