no code implementations • ECCV 2020 • Chi-Chong Wong, Chi-Man Vong
Large-scale point cloud semantic understanding is an important problem in self-driving cars and autonomous robotics navigation.
no code implementations • CVPR 2023 • Chi-Chong Wong
A novel Transformer model called MeshFormer is proposed, which i) integrates Heat Diffusion method into Multi-head Self-Attention operation (HDMSA) to adaptively capture the features from local neighborhood to global contexts; ii) applies a novel Heat Kernel Signature based Structure Encoding (HKSSE) to embed the intrinsic geometric structures of mesh instances into Transformer for structure-aware processing.
no code implementations • ICCV 2021 • Chi-Chong Wong, Chi-Man Vong
Current deep learning and graph machine learning methods fail to tackle such challenges and thus provide inferior performance in fine-grained 3D analysis.