Tuan Duc Ngo

Working on 3D & 4D Vision

I’m a PhD student in Computer Science at UMass Amherst, advised by Prof. Evangelos Kalogerakis and Prof. Chuang Gan.

I was a research intern at Adobe Research. Previously, I interned at Snap Research, working with Dr. Chaoyang Wang on 4D reconstruction.

Prior to my Ph.D., I was an AI Research Resident at VinAI Research, working closely with Dr. Khoi Nguyen.

UMass Amherst

PhD in CS

Sep 2023 -

News

[06/2026] I will join Meta as a Research Intern.
[02/2026] DAGE is accepted to CVPR 2026 [code].
[05/2025] I joined Adobe Research as a Research Intern.
[02/2025] 4Real-Video is accepted (highlight) to CVPR 2025.
[01/2025] DELTA is accepted to ICLR 2025 [code].
[05/2024] I joined Snap Research as a Research Intern.
[02/2024] Open3DIS is accepted to CVPR 2024 code].
[07/2023] GaPro is accepted to ICCV 2023 [code].
[02/2023] ISBNet is accepted to CVPR 2023 [code].
[07/2022] GeoFormer is accepted to ECCV 2022 [code].

▼ Show more

Publications

* indicates equal contribution.

DAGE: Dual-Stream Architecture for Efficient and Fine-Grained Geometry Estimation

Tuan Duc Ngo, Jiahui Huang, Seoung Wug Oh, Kevin Blackburn-Matzen, Evangelos Kalogerakis, Chuang Gan, Joon-Young Lee

CVPR, 2026

Estimate accurate camera poses and high-fidelity 3D geometry at 2K resolution via an efficient dual-stream architecture.

Project Page PDF arXiv Code

DELTAv2: Accelerating Dense 3D Tracking

Tuan Duc Ngo, Ashkan Mirzaei, Guocheng Qian, Hanwen Liang, Chuang Gan, Evangelos Kalogerakis, Peter Wonka, Chaoyang Wang

Preprint, 2025

Accelerate dense, long-range, 3D point tracking with 5-100x speedup

Project Page PDF arXiv Code

4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion

Chaoyang Wang*, Peiye Zhuang*, Tuan Duc Ngo*, Willi Menapace, Aliaksandr Siarohin, Michael Vasilkovsky, Ivan Skorokhodov, Sergey Tulyakov, Peter Wonka, Hsin-Ying Lee

CVPR, 2025 Highlight

A diffusion model that generates 4D video -- a grid of video frames with both time and viewpoint axes.

Project Page PDF arXiv

DELTA: Dense Efficient Long-range 3D Tracking for Any video

Tuan Duc Ngo, Peiye Zhuang, Chuang Gan, Evangelos Kalogerakis, Sergey Tulyakov, Hsin-Ying Lee, Chaoyang Wang

ICLR, 2025

Capture the dense, long-range, 3D point trajectories from casual videos in a feed-forward manner

Project Page PDF arXiv Code

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

Phuc Nguyen*, Tuan Duc Ngo*, Chuang Gan, Evangelos Kalogerakis, Anh Tran, Cuong Pham, Khoi Nguyen

CVPR, 2024

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

Project Page PDF arXiv Code

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

Tuan Duc Ngo, Binh-Son Hua, Khoi Nguyen

ICCV, 2023

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

PDF arXiv Code

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

Tuan Duc Ngo, Binh-Son Hua, Khoi Nguyen

CVPR, 2023

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

PDF arXiv Code Video

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

Tuan Duc Ngo, Khoi Nguyen

ECCV, 2022

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

PDF arXiv Code

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

Minh-Quan Viet Bui*, Tuan Duc Ngo*, Hoang-Anh Pham, Duc Dung Nguyen

PeerJ, 2021

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

PDF Code

Academic Services

Teaching Assistant Intelligent Visual Computing (COMPSCI 674, Spring 2024) Game Programming (COMPSCI 576, Fall 2024)

Conference Reviewer CVPR '24/'25/'26 ICCV '25 ECCV '24/'26 NeurIPS '25 ICLR '26 AAAI '25/'26

Journal Reviewer IEEE Transactions on Image Processing