Zelong Tan — accepted AI-conference papers

2026

Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learning

YIYAO MA, Kai Chen, Zhongxiang Zhou, Zhuheng Song, Dongsheng Xie, Zelong Tan +2

ICML 2026poster

Monocular 3D shape recovery is fundamental to geometric understanding, yet achieving robust generalization across arbitrary viewpoints and unseen object categories remains a significant challenge. In this paper, we present a generalizable deformation learning framework that reconstructs 3D objects b…

Cited by 0 Source ↗Scholar ↗

2026

Preserving Topological and Geometric Embeddings for Point Cloud Recovery

Kaiyue Zhou, Zelong Tan, Hongxiao Wang, Ya-Li Li, Shengjin Wang

AAAI 2026technical

Recovering point clouds involves the sequential process of sampling and restoration, yet existing methods struggle to effectively leverage both topological and geometric attributes. To address this, we propose an end-to-end architecture named TopGeoFormer, which maintains these critical properties t

Cited by 0 Source ↗PDF ↗Scholar ↗