Sheldon Fung — accepted AI-conference papers

2026

SuP: Sub-cloud Driven Point Cloud Registration

Sheldon Fung, Wei Pan, Ling Cao, Fei Hou, Ling Chen, Shasha Mao +2

CVPR 2026

While existing point-cloud-registration methods can well handle high-overlap scenarios of two point clouds, they often struggle with low-overlap scenarios, due to inevitable geometric/semantic ambiguities in the non-overlapping regions. In this paper, we introduce SuP, a novel framework that reformu

Cited by 0 Source ↗code ↗Scholar ↗

2024

SemReg: Semantics Constrained Point Cloud Registration

Sheldon Fung, Xuequan Lu*, Dasith de Silva Edirimuni, Wei Pan, Xiao Liu, HONGDONG LI

ECCV 2024poster

"Despite the recent success of Transformers in point cloud registration, the cross-attention mechanism, while enabling point-wise feature exchange between point clouds, suffers from redundant feature interactions among semantically unrelated regions. Additionally, recent methods rely only on 3D info…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗