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

TL;DR

CylinderPlane introduces a cylindrical coordinate-based implicit representation for 3D-aware image generation, effectively eliminating symmetry artifacts and enabling high-quality, multi-scale 360° view synthesis with improved consistency and detail.

Contribution

The paper proposes CylinderPlane, a novel cylindrical coordinate system-based implicit representation that addresses symmetry artifacts and enhances multi-view 360° image synthesis.

Findings

Achieves artifact-free 360° image generation

Outperforms previous methods in synthetic and real datasets

Supports multi-scale feature learning and robustness

Abstract

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.