| CARVIEW |
Binh-Son Hua
Assistant Professor, Trinity College Dublin
binhson.hua (at) tcd.ie / binhson.hua (at) gmail
My current research interests are in the intersection of computer graphics and computer vision, where I focus on developing deep learning techniques for realistic image and 3D synthesis.
Mar 2025: My group currently have the following open positions to fill: a postdoctoral researcher, a research assistant, and a PhD student.
Please submit your application package directly to me via email. Kindly note that only shortlisted candidates will be contacted.
Before joining TCD, I was a Research Scientist at VinAI, the first AI research lab in Vietnam with a focus on fundamental research in 2020-2023. I did my postdoctoral research on physically based rendering with Dr. Toshiya Hachisuka at the University of Tokyo, and on 3D deep learning with Dr. Sai-Kit Yeung at Singapore University of Technology and Design. I received my PhD at National University of Singapore in 2015, working with Dr. Kok-Lim Low.
News
Jul 17, 2024: Two papers accepted to ECCV 2024 (diverse text-to-3D generation, and underwater instance visual description)
Feb 27, 2024: Two papers accepted to CVPR 2024 (object insertion and removal for NeRFs, and underwater image segmentation).
Aug 04, 2023: A co-authored conference paper on Monte Carlo image denoising accepted to SIGGRAPH Asia 2023.
July 14, 2023: Three papers accepted to ICCV 2023 (Stylized neural radiance fields, 360-degree neural scene decoration, and 3D point cloud instance segmentation).
June 22, 2023: Two papers accepted to IROS 2023.
June 20, 2023: I will serve as Area Chair for CVPR 2024.
June 07, 2023: I was recognized as a CVPR 2023 Outstanding Reviewer.
Mar 01, 2023: One paper accepted to CVPR 2023 (3D point cloud instance segmentation)
Oct 11, 2022: Two papers accepted to WACV 2023 (GAN inversion for 3D point clouds, single-image HDR reconstruction) and a paper accepted to ACCV 2022 (self-supervised point cloud learning with multiple-view rendering).
July 04, 2022: Four papers accepted to ECCV 2022 with the following topics: neural scene decoration, 4D point cloud reconstruction, text-to-image synthesis, and few-shot video classification.
-
June 17, 2022: A paper about style transfer for architectural photographs accepted to ICCP 2022.
Mar 26, 2022: Two co-author papers about Monte Carlo rendering accepted to SIGGRAPH North America 2022.
-
Mar 03, 2022: A paper on GAN inversion accepted to CVPR 2022.
Feb 14, 2022: An extended version of RIConv++, a simple rotation invariant convolution for point clouds, accepted to IJCV journal 2022.
-
Oct 20, 2021: A co-author paper on neural sequence transformation was presented at Pacific Graphics 2021 (Computer Graphics Forum).
Sep 29, 2021: A paper on few-shot learning accepted at NeurIPS 2021.
July 23, 2021: Two papers on 3D point cloud learning accepted at ICCV 2021.
June 12, 2021: Two papers on medical segmentation are accepted at MICCAI 2021.
Jan 13, 2021: A paper on network pruning (that retraining with proper learning rate schedules matters) is accepted at ICLR 2021!
Research
- 2023
-
ISBNet: a 3D Point Cloud Instance Segmentation Network
with Instance-aware Sampling and Box-aware Dynamic ConvolutionTuan Duc Ngo, Binh-Son Hua, Khoi Nguyen
CVPR 2023
-
-
- 2022
-
-
-
-
-
-
-
-
-
-
-
- 2021
-
Single-Click 3D Object Annotation on LiDAR Point Clouds
Trung Nguyen, Binh-Son Hua, Duc Thanh Nguyen, Dinh Phung
NeurIPS Data-Centric AI Workshop 2021
-
POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples
Duong H. Le*, Khoi D. Nguyen*, Khoi Nguyen, Quoc-Huy Tran, Rang Nguyen, Binh-Son Hua
NeurIPS 2021
-
Neural Sequence Transformation
Sabyasachi Mukherjee, Sayan Mukherjee, Binh-Son Hua, Nobuyuki Umetani, Daniel Meister
Computer Graphics Forum (Proceedings of Pacific Graphics) 2021
-
Point-set Distances for Learning Representations of 3D Point Clouds
Trung Nguyen, Quang-Hieu Pham, Tam Le, Tung Pham, Nhat Ho, Binh-Son Hua
ICCV 2021
-
Minimal Adversarial Examples for Deep Learning on 3D Point Clouds
Jaeyeon Kim, Binh-Son Hua, Duc Thanh Nguyen, Sai-Kit Yeung
ICCV 2021
-
3D-UCaps: 3D Capsules Unet for Volumetric Image Segmentation
Tan Nguyen, Binh-Son Hua, Ngan Le
MICCAI 2021 (Oral)
-
Point-Unet: A Context-aware Point-based Neural Network for Volumetric Segmentation
Ngoc-Vuong Ho, Tan Nguyen, Gia-Han Diep, Ngan Le, Binh-Son Hua
MICCAI 2021
-
Network Pruning That Matters: A Case Study on Retraining Variants
Duong H. Le, Binh-Son Hua
ICLR 2021
- 2020
-
Global Context Aware Convolutions for 3D Point Cloud Understanding
Zhiyuan Zhang, Binh-Son Hua, Wei Chen, Yibin Tian, and Sai-Kit Yeung
3DV 2020 (Oral)
-
Deep Combiner for Independent and Correlated Pixel Estimates
Jonghee Back, Binh-Son Hua, Toshiya Hachisuka, and Bochang Moon
SIGGRAPH Asia 2020
-
LCD: Learned Cross-Domain Descriptors for 2D-3D Matching
Quang-Hieu Pham, Mikaela Angelina Uy, Binh-Son Hua, Duc Thanh Nguyen, Gemma Roig, and Sai-Kit Yeung
AAAI 2020 (Oral)
- 2019
-
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data
Mikaela Angelina Uy, Quang-Hieu Pham, Binh-Son Hua, Duc Thanh Nguyen, and Sai-Kit Yeung
ICCV 2019 (Oral)
-
ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics
Zhiyuan Zhang, Binh-Son Hua, and Sai-Kit Yeung
ICCV 2019 (Oral)
-
Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
Zhiyuan Zhang, Binh-Son Hua, David W. Rosen, and Sai-Kit Yeung
3DV 2019
-
A Survey on Gradient-Domain Rendering
Binh-Son Hua*, Adrien Gruson*, Victor Petitjean, Matthias Zwicker, Derek Nowrouzezahrai, Elmar Eisemann, and Toshiya Hachisuka
Eurographics 2019 State of the Art Reports
-
JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds
with Multi-Task Pointwise Networks and Multi-Value Conditional Random FieldsQuang-Hieu Pham, Duc Thanh Nguyen, Binh-Son Hua, Gemma Roig, and Sai-Kit Yeung
CVPR 2019 (Oral)
-
Real-time Progressive 3D Semantic Segmentation for Indoor Scene
Quang-Hieu Pham, Binh-Son Hua, Duc Thanh Nguyen, and Sai-Kit Yeung
WACV 2019
- 2018
-
Light Transport Simulation in the Gradient Domain
Binh-Son Hua, Adrien Gruson, Matthias Zwicker, and Toshiya Hachisuka
SIGGRAPH Asia 2018 Courses
-
Language-Driven Synthesis of 3D Scenes from Scene Databases
Rui Ma, Akshay Gadi Patil, Matthew Fisher, Manyi Li, Sören Pirk, Binh-Son Hua, Sai-Kit Yeung, Xin Tong, Leonidas Guibas, Hao Zhang
SIGGRAPH Asia 2018
-
Creating and Understanding 3D Annotated Scene Meshes
Zhiyuan Zhang, Binh-Son Hua, Duc Thanh Nguyen, Lap-Fai Yu, Sai-Kit Yeung, and Daniela Rus
Invited Speaker: Sai-Kit Yeung and Quang-Hieu Pham
IROS 2018 Tutorial
-
Gradient-domain Volumetric Photon Density Estimation
Adrien Gruson, Binh-Son Hua, Nicolas Vibert, Derek Nowrouzezahrai, and Toshiya Hachisuka
SIGGRAPH 2018
-
-
Creating Annotated Scene Meshes for Training and Testing Robot Systems
Binh-Son Hua, Duc Thanh Nguyen, Lap-Fai Yu, Sai-Kit Yeung, and Daniela Rus
Invited Speakers: Duc Thanh Nguyen and Quang-Hieu Pham
ICRA 2018 Tutorial
-
SHREC’18: RGB-D Object-to-CAD Retrieval
Quang-Hieu Pham, Binh-Son Hua, Lap-Fai Yu, Duc Thanh Nguyen, and Sai-Kit Yeung
Eurographics Workshop on 3D Object Retrieval 2018
- 2017
-
A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation
Duc Thanh Nguyen*, Binh-Son Hua*, Lap-Fai Yu, and Sai-Kit Yeung (*) Equal contributation
TVCG 2017
-
Gradient-Domain Photon Density Estimation
Binh-Son Hua, Adrien Gruson, Derek Nowrouzezahrai, and Toshiya Hachisuka
Eurographics 2017
-
SHREC’17: RGB-D to CAD Retrieval with ObjectNN Dataset
Binh-Son Hua, Quang-Trung Truong, Minh-Khoi Tran, Quang-Hieu Pham, Lap-Fai Yu, Duc Thanh Nguyen, and Sai-Kit Yeung
(with 18 amazing participants in 5 groups)
Eurographics Workshop on 3D Object Retrieval 2017
- 2016
-
SceneNN: A Scene Meshes Dataset with aNNotations
Binh-Son Hua, Quang-Hieu Pham, Duc Thanh Nguyen, Minh-Khoi Tran, Lap-Fai Yu, and Sai-Kit Yeung
3DV 2016 (Best Paper Honorable Mention)
-
A Field Model for Repairing 3D Shapes
Duc Thanh Nguyen, Binh-Son Hua, Minh-Khoi Tran, Quang-Hieu Pham, and Sai-Kit Yeung
CVPR 2016 (Spotlight)
- 2015 and before
-
Guided Path Tracing Using Clustered Virtual Point Lights
Binh-Son Hua and Kok-Lim Low
SIGGRAPH Asia 2015 Posters Program
-
Calibration of Depth Cameras Using Denoised Depth Images
Ramanpreet Pahwa, Minh Do, Tian-Tsong Ng, and Binh-Son Hua
ICIP 2014
-
-
Direct and Progressive Reconstruction of Dual Photography Images
Binh-Son Hua, Imari Sato, and Kok-Lim Low
ICIP 2013
-
Reconstruction of Depth and Normals from Interreflections
Binh-Son Hua, Tian-Tsong Ng, and Kok-Lim Low
ICIP 2013
-
-
Adaptive Energy Diffusion for Blind Inverse Halftoning
Lei Wang, Binh-Son Hua, and Xueqing Li
PCM 2010
Last update: Oct 27, 2022