Thambipillai Srikanthan — accepted AI-conference papers

2024

GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding

Changshuo Wang*, Meiqing Wu, Siew-Kei Lam, Xin Ning, Shangshu Yu, Ruiping Wang +2

ECCV 2024poster

"Despite the significant advancements in pre-training methods for point cloud understanding, directly capturing intricate shape information from irregular point clouds without reliance on external data remains a formidable challenge. To address this problem, we propose GPSFormer, an innovative Globa…

Cited by 20 Source ↗PDF ↗code ↗Scholar ↗

2024

Hierarchical Object-Aware Dual-Level Contrastive Learning for Domain Generalized Stereo Matching

Yikun Miao, Meiqing Wu, Siew Kei Lam, Changsheng Li, Thambipillai Srikanthan

NeurIPS 2024poster

Stereo matching algorithms that leverage end-to-end convolutional neural networks have recently demonstrated notable advancements in performance. However, a common issue is their susceptibility to domain shifts, hindering their ability in generalizing to diverse, unseen realistic domains. We argue t…

Cited by 0 Source ↗PDF ↗Scholar ↗