Tri-Plane Representations

Follow this topic Ask about this topic

Latest papers

8 papers0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Owner3D: Ownership-Guided Style Writing for Training-Free Localized 3D Stylization
Aug 14, 2026Suchang Tao, Kaifeng Shi, Zhiyan Liu +2Tri-Plane Representations 3D Scene Representation
College of Computer Science, Sichuan University, Chengdu, China
A Geometry-Aware Triplane Field Network for Vehicle Aerodynamic Prediction
Jun 5, 2026Kangkang Qi, Huiyu Yang, Keqi Ding +5PDE Surrogate Modeling Tri-Plane Representations
Department of Mechanics and Aerospace Engineering, Southern University of Science and Technology, Shenzhen 518055, China · Shenzhen Key Laboratory of Complex Aerospace Flows, Southern University of Science and Technology, Shenzhen 518055, China · Shenzhen Tenfong Technology Co., Ltd., Shenzhen 518000, China +1
HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image
Jun 1, 2026Hezhen Hu, Wangbo Zhao, Lanqing Guo +63D Avatar Generation Tri-Plane Representations
University of Texas at Austin · National University of Singapore · Texas A&M University
CATRF: Codec-Adaptive TriPlane Radiance Fields for Volumetric Content Delivery
May 18, 2026Tung-I Chen, Lingdong Wang, Subhransu Maji +1Tri-Plane Representations Rate-Distortion Optimization
University of Massachusetts Amherst
GaussianSSC: Triplane-Guided Directional Gaussian Fields for 3D Semantic Completion
Mar 23, 2026Ruiqi Xian, Jing Liang, He Yin +2Tri-Plane Representations 3D Scene Completion
CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View Synthesis
Mar 6, 2026Qiwei Wang, Xianghui Ze, Jingyi Yu +1Tri-Plane Representations Novel View Synthesis
Shanghaitech University · Nanjing University of Science and Technology
Equivariant Volumetric Grasping
Jul 24, 2025Pinhao Song, Yutong Hu, Pengteng Li +1Tri-Plane Representations Robotic Grasping
KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics. · AI Thrust, HKUST(GZ) · KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images.
NumGrad-Pull: Numerical Gradient Guided Tri-plane Representation for Surface Reconstruction from Point Clouds
Nov 26, 2024Ruikai Cui, Binzhu Xie, Shi Qiu +3Implicit Neural Representations 3D Reconstruction
School of Computing, The Australian National University, Australia · Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China · Department of Computer Science & Software Engineering, the University of Western Australia, Australia

Aug 14, 2026J/K move · Enter open · S save

Owner3D: Ownership-Guided Style Writing for Training-Free Localized 3D Stylization

Suchang Tao, Kaifeng Shi, Zhiyan Liu, Zhuoyuan Jiang+1

College of Computer Science, Sichuan University, Chengdu, China

Tri-Plane Representations 3D Scene Representation

Open paper AskPDF arXiv

Localized 3D stylization aims to modify the appearance of a specified object part while preserving the remaining surfaces. In large reconstruction models (LRMs), this task is challenging because style is injected into intermediate appearance representations before rendering, while compact triplane features are shared across target and non-target surfaces, causing style leakage and boundary ambiguity. We propose Owner3D, a training-free framework for localized 3D stylization that integrates localized appearance control directly into the LRM reconstruction process. Specifically, Owner3D introduces ownership-guided style writing to restrict reference-style injection to target regions, producing a single localized stylized triplane without additional training while avoiding separate global style and appearance representations. To resolve appearance ambiguity near semantic boundaries, we further introduce boundary dual slots that maintain separate local feature sources for target and non-target regions. Finally, a surface-first texture readout hierarchically combines surface, 3D, and triplane ownership evidence to robustly recover appearance under incomplete visibility. Experiments on a benchmark constructed from Google Scanned Objects and PartNet demonstrate that Owner3D consistently outperforms existing 3D stylization methods in target-region style fidelity and non-target appearance preservation, reducing appearance leakage by 86.4% and 89.9% compared with StyleSplat and LAENeRF, respectively.