Hello, I'm Tuan Duc Ngo

I am a first-year PhD student in Computer Science of UMass Amherst, USA, advised by Prof. Evangelos Kalogerakis and Prof. Chuang Gan. Prior to that, I was an AI Research Resident at VinAI Research. I received my B.E. degree in Computer Engineering from the Ho Chi Minh City University of Technology, Vietnam. Email: ductuan.ngo99 (at) gmail (dot) com


News

  • May 2024: I joined Snap Research as a Research Intern.
  • Feb 2024: Open3DIS has been accepted to CVPR 2024. We have also released the code.
  • Jul 2023: GaPro has been accepted to ICCV 2023. We have also released the code.
  • Feb 2023: ISBNet has been accepted to CVPR 2023. We have also released the code.
  • Jul 2022: GeoFormer has been accepted to ECCV 2022. We have also released the code.

Publications

Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance

Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance

CVPR, 2024

Tackle the open-vocabulary 3D point cloud instance segmentation by using 2D prior

GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers

GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers

ICCV, 2023

Tackle the box-supervised 3D point cloud instance segmentation by using Gaussian Processes to generate pseudo labels

ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution

ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution

CVPR, 2023

Introduce an efficient sampling strategy and propose leveraging the bounding box as a geometric cue for the 3D point cloud instance segmentation

Geodesic-Former: A Geodesic-Guided Few-Shot 3D Point Cloud Instance Segmenter

Geodesic-Former: A Geodesic-Guided Few-Shot 3D Point Cloud Instance Segmenter

Tuan Ngo*, Khoi Nguyen
ECCV, 2022

Propose a new task, Few-shot 3D point cloud instance segmentation, and introduce a geodesic-based 3D instance segmenter

GAC3D: improving monocular 3D object detection with ground-guide model and adaptive convolution

GAC3D: improving monocular 3D object detection with ground-guide model and adaptive convolution

PeerJ, 2021

Propose a new monocular 3D detection framework leveraging the ground plane model and depth-adaptive convolution