CylinderPlane: Nested Cylinder Representation for 3D-aware Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jia, Ru, Ma, Xiaozhuang, Wang, Jianji, Zheng, Nanning
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909697893728256
author Jia, Ru
Ma, Xiaozhuang
Wang, Jianji
Zheng, Nanning
author_facet Jia, Ru
Ma, Xiaozhuang
Wang, Jianji
Zheng, Nanning
contents While the proposal of the Tri-plane representation has advanced the development of the 3D-aware image generative models, problems rooted in its inherent structure, such as multi-face artifacts caused by sharing the same features in symmetric regions, limit its ability to generate 360$^\circ$ view images. In this paper, we propose CylinderPlane, a novel implicit representation based on Cylindrical Coordinate System, to eliminate the feature ambiguity issue and ensure multi-view consistency in 360$^\circ$. Different from the inevitable feature entanglement in Cartesian coordinate-based Tri-plane representation, the cylindrical coordinate system explicitly separates features at different angles, allowing our cylindrical representation possible to achieve high-quality, artifacts-free 360$^\circ$ image synthesis. We further introduce the nested cylinder representation that composites multiple cylinders at different scales, thereby enabling the model more adaptable to complex geometry and varying resolutions. The combination of cylinders with different resolutions can effectively capture more critical locations and multi-scale features, greatly facilitates fine detail learning and robustness to different resolutions. Moreover, our representation is agnostic to implicit rendering methods and can be easily integrated into any neural rendering pipeline. Extensive experiments on both synthetic dataset and unstructured in-the-wild images demonstrate that our proposed representation achieves superior performance over previous methods.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15606
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CylinderPlane: Nested Cylinder Representation for 3D-aware Image Generation
Jia, Ru
Ma, Xiaozhuang
Wang, Jianji
Zheng, Nanning
Computer Vision and Pattern Recognition
68T45
I.4.5
While the proposal of the Tri-plane representation has advanced the development of the 3D-aware image generative models, problems rooted in its inherent structure, such as multi-face artifacts caused by sharing the same features in symmetric regions, limit its ability to generate 360$^\circ$ view images. In this paper, we propose CylinderPlane, a novel implicit representation based on Cylindrical Coordinate System, to eliminate the feature ambiguity issue and ensure multi-view consistency in 360$^\circ$. Different from the inevitable feature entanglement in Cartesian coordinate-based Tri-plane representation, the cylindrical coordinate system explicitly separates features at different angles, allowing our cylindrical representation possible to achieve high-quality, artifacts-free 360$^\circ$ image synthesis. We further introduce the nested cylinder representation that composites multiple cylinders at different scales, thereby enabling the model more adaptable to complex geometry and varying resolutions. The combination of cylinders with different resolutions can effectively capture more critical locations and multi-scale features, greatly facilitates fine detail learning and robustness to different resolutions. Moreover, our representation is agnostic to implicit rendering methods and can be easily integrated into any neural rendering pipeline. Extensive experiments on both synthetic dataset and unstructured in-the-wild images demonstrate that our proposed representation achieves superior performance over previous methods.
title CylinderPlane: Nested Cylinder Representation for 3D-aware Image Generation
topic Computer Vision and Pattern Recognition
68T45
I.4.5
url https://arxiv.org/abs/2507.15606