George Kiyohiro Nakayama — accepted AI-conference papers

2024

Semantic-Aware Transformation-Invariant RoI Align

Guo-Ye Yang, George Kiyohiro Nakayama, Zi-Kai Xiao, Tai-Jiang Mu, Xiaolei Huang, Shi-Min Hu

AAAI 2024technical

Great progress has been made in learning-based object detection methods in the last decade. Two-stage detectors often have higher detection accuracy than one-stage detectors, due to the use of region of interest (RoI) feature extractors which extract transformation-invariant RoI features for differe…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion

George Kiyohiro Nakayama, Mikaela Angelina Uy, Jiahui Huang, Shi-Min Hu, Ke Li, Leonidas Guibas

ICCV 2023poster

While the community of 3D point cloud generation has witnessed a big growth in recent years, there still lacks an effective way to enable intuitive user control in the generation process, hence limiting the general utility of such methods. Since an intuitive way of decomposing a shape is through its…

Cited by 29 PDF ↗Scholar ↗