Biography
Binh-Son Hua is an Assistant Professor of Computer Science at Trinity College Dublin. His research interests are at the intersection of computer graphics, computer vision, and machine learning with a focus on generative AI in the 3D space, particularly on 3D content generation and rendering using generative AI techniques. He received his PhD in Computer Science from National University of Singapore, and spent his postdoctoral research at The University of Tokyo, Japan and Singapore University of Technology and Design. He was recognized with the Best Paper Honorable Mention award at International Conference on 3D Vision 2016, and as an Outstanding Reviewer at CVPR 2023. He has been actively serving as an area chair for CVPR, and as a technical program committee member for SIGGRAPH Asia. His research is funded by Research Ireland under the Frontiers for the Future Programme.
Publications and Further Research Outputs
Peer-Reviewed Publications
Do, Khoi and Hua, Binh-Son, Text-to-3D Generation using Jensen-Shannon Score Distillation, International Conference on 3D Vision (3DV), 2026
Vu, Tuan-Anh and Hai, Nguyen Truong and Zheng, Ziqiang and Hua, Binh-Son and Guo, Qing and Tsang, Ivor and Yeung, Sai-Kit, Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues, WACV, 2026
Pham, Phuc and Tran, Uy Dieu and Hua, Binh-Son and Nguyen, Phong, Efficient 3D Garment Generation with Geometry Image Representation, CVPR, 2026
Vu, Tuan-Anh and Nguyen, Duc Thanh and Guo, Qing and Chung, Nhat and Hua, Binh-Son and Tsang, Ivor W and Yeung, Sai-Kit, Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion, International Journal of Computer Vision (IJCV), 2026
Zheng, Ziqiang and Wong, Yuk-Kwan and Hua, Binh-Son and Shi, Jianbo and Yeung, Sai-Kit, CoralSRT: Revisiting Coral Reef Semantic Segmentation by Feature Rectification via Self-supervised Guidance, ICCV, 2025
Nguyen-Truong, Hai and Nguyen, E-Ro and Vu, Tuan-Anh and Tran, Minh-Triet and Hua, Binh-Son and Yeung, Sai-Kit, Vision-Aware Text Features in Referring Image Segmentation: From Object Understanding to Context Understanding, WACV, 2025
Chen, Yingshu and Shao, Guocheng and Shum, Ka Chun and Hua, Binh-Son and Yeung, Sai-Kit, Advances in 3D Neural Stylization: A Survey, International Journal of Computer Vision (IJCV), 2025
Kompanowski, Hubert and Hua, Binh-Son, Dream-in-Style: Text-to-3D Generation using Stylized Score Distillation, International Conference on 3D Vision (3DV), 2025
Khoi Do, Duong Nguyen, Nam-Khanh Le, Quoc-Viet Pham, Binh-Son Hua, Won-Joo Hwang, Domain Generalization via Pareto Optimal Gradient Matching, European Conference on Artificial Intelligence (ECAI), 2025, 2025
Shum, Ka Chun and Hua, Binh-Son and Nguyen, Duc Thanh and Yeung, Sai-Kit, Color Alignment in Diffusion, CVPR, 2025
Vu, Tuan-Anh and Sarkar, Srinjay and Zhang, Zhiyuan and Hua, Binh-Son and Yeung, Sai-Kit, Test-Time Augmentation for 3D Point Cloud Classification and Segmentation, International Conference on 3D Vision (3DV) 2024, 2024
Shum, Ka Chun and Kim, Jaeyeon and Hua, Binh-Son and Nguyen, Duc Thanh and Yeung, Sai-Kit, Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updates, CVPR, 2024
Ziqiang Zheng, Haixin Liang, Binh-Son Hua, Yue Him Wong, Put ANG Jr, Apple Pui Yi CHUI, Sai-Kit Yeung, CoralSCOP: Segment any Coral Image on this Planet, CVPR, 2024
Zheng, Ziqiang and Chen, Yiwei and Zeng, Huimin and Vu, Tuan-Anh and Hua, Binh-Son and Yeung, Sai-Kit, MarineInst: A Foundation Model for Marine Image Analysis with Instance Visual Description, ECCV, 2024
Tran, Uy Dieu and Luu, Minh and Nguyen, Phong and Nguyen, Khoi and Hua, Binh-Son, DiverseDream: Diverse Text-to-3D Synthesis with Augmented Text Embedding, ECCV, 2024
Zheng, Ziqiang and Chen, Yingshu and Hua, Binh-Son and Wu, Yang and Yeung, Sai-Kit, Cross-Domain Autonomous Driving Perception using Contrastive Appearance Adaptation, IROS 2023, 2023
Ngo, Tuan Duc and Hua, Binh-Son and Nguyen, Khoi, ISBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution, CVPR 2023, 2023
Pang, Hong-Wing and Hua, Binh-Son and Yeung, Sai-Kit, Locally Stylized Neural Radiance Fields, ICCV 2023, 2023
Kim, Jaeyeon and Hua, Binh-Son and Nguyen, Duc Thanh and Yeung, Sai-Kit, PointInverter: Point Cloud Reconstruction and Editing via a Generative Model with Shape Priors, WACV, 2023
Shum, Ka Chun and Pang, Hong-Wing and Hua, Binh-Son and Nguyen, Duc Thanh and Yeung, Sai-Kit, Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decoration, ICCV 2023, 2023
Zheng, Ziqiang and Chen, Yingshu and Hua, Binh-Son and Yeung, Sai-Kit, CompUDA: Compositional Unsupervised Domain Adaptation for Semantic Segmentation under Adverse Conditions, IROS 2023, 2023
Back, Jonghee and Hua, Binh-Son and Hachisuka, Toshiya and Moon, Bochang, Input-Dependent Uncorrelated Weighting for Monte Carlo Denoising, SIGGRAPH Asia Conference, 2023
Le, Phuoc-Hieu and Le, Quynh and Nguyen, Rang and Hua, Binh-Son, Single-Image HDR Reconstruction by Multi-Exposure Generation, WACV, 2023
Ngo, Tuan Duc and Hua, Binh-Son and Nguyen, Khoi, GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelers, ICCV 2023, 2023
Chen, Yingshu and Vu, Tuan-Anh and Shum, Ka-Chun and Hua, Binh-Son and Yeung, Sai-Kit, Time-of-Day Neural Style Transfer for Architectural Photographs, ICCP 2022, 2022
Back, Jonghee and Hua, Binh-Son and Hachisuka, Toshiya and Moon, Bochang, Self-Supervised Post-Correction for Monte Carlo Denoising, SIGGRAPH Conference Proceedings, 2022
Zhang, Zhiyuan and Hua, Binh-Son and Yeung, Sai-Kit, RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning, International Journal of Computer Vision (IJCV), 2022
Nguyen, Khoi D and Tran, Quoc-Huy and Nguyen, Khoi and Hua, Binh-Son and Nguyen, Rang, Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments, ECCV 2022, 2022
Salaun, Corentin and Gruson, Adrien and Hua, Binh-Son and Hachisuka, Toshiya and Singh, Gurprit, Regression-based Monte Carlo integration, ACM Transactions on Graphics (TOG), 41, (4), 2022, p1--14
Tran, Minh and Ly, Loi and Hua, Binh-Son and Le, Ngan, SS-3DCapsNet: Self-supervised 3D Capsule Networks for Medical Segmentation on Less Labeled Data, The IEEE International Symposium on Biomedical Imaging (ISBI) 2022, 2022
Pang, Hong-Wing and Chen, Yingshu and Hua, Binh-Son and Yeung, Sai-Kit, Neural Scene Decoration from a Single Photograph, ECCV 2022, 2022
Tran, Bach and Hua, Binh-Son and Tran, Anh Tuan and Hoai, Minh, Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysis, ACCV, 2022
Dinh, Tan M and Tran, Anh Tuan and Nguyen, Rang and Hua, Binh-Son, HyperInverter: Improving StyleGAN Inversion via Hypernetwork, CVPR 2022, 2022
Dinh, Tan M and Nguyen, Rang and Hua, Binh-Son, TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation, ECCV 2022, 2022
Vu, Tuan-Anh and Nguyen, Duc-Thanh and Hua, Binh-Son and Pham, Quang-Hieu and Yeung, Sai-Kit, RFNet-4D: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds, ECCV 2022, 2022
Kim, Jaeyeon and Hua, Binh-Son and Nguyen, Duc Thanh and Yeung, Sai-Kit, Minimal Adversarial Examples for Deep Learning on 3D Point Clouds, International Conference on Computer Vision (ICCV), 2021
Le, Duong Hoang and Nguyen, Khoi Duc and Nguyen, Khoi and Tran, Quoc-Huy and Nguyen, Rang and Hua, Binh-Son, POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples, Neural Information Processing Systems, 2021
Mukherjee, Sabyasachi and Mukherjee, Sayan and Hua, Binh-Son and Umetani, Nobuyuki and Meister, Daniel, Neural Sequence Transformation, Computer Graphics Forum, 2021
Le, Duong H and Hua, Binh-Son, Network Pruning That Matters: A Case Study on Retraining Variants, International Conference on Learning Representations (ICLR), 2021
Nguyen, Trung and Pham, Quang-Hieu and Le, Tam and Pham, Tung and Ho, Nhat and Hua, Binh-Son, Point-set Distances for Learning Representations of 3D Point Clouds, International Conference on Computer Vision (ICCV), 2021
Nguyen, Tan and Hua, Binh-Son and Le, Ngan, 3d-ucaps: 3d capsules unet for volumetric image segmentation, Medical Image Computing and Computer Assisted Intervention (MICCAI), 2021, pp548--558
Ho, Ngoc-Vuong and Nguyen, Tan and Diep, Gia-Han and Le, Ngan and Hua, Binh-Son, Point-unet: A context-aware point-based neural network for volumetric segmentation, Medical Image Computing and Computer Assisted Intervention (MICCAI), 2021, pp644--655
Nguyen, Trung and Hua, Binh-Son and Nguyen, Duc Thanh and Phung, Dinh, Single-Click 3D Object Annotation on LiDAR Point Clouds, NeurIPS Data Centric AI (DCAI) workshop, 2021
Pham, Quang-Hieu and Uy, Mikaela Angelina and Hua, Binh-Son and Nguyen, Duc Thanh and Roig, Gemma and Yeung, Sai-Kit, LCD: Learned Cross-Domain Descriptors for 2D-3D Matching, AAAI Conference on Artificial Intelligence, 2020
Back, Jonghee and Hua, Binh-Son and Hachisuka, Toshiya and Moon, Bochang, Deep Combiner for Independent and Correlated Pixel Estimates, SIGGRAPH Asia, 2020
Zhang, Zhiyuan and Hua, Binh-Son and Chen, Wei and Tian, Yibin and Yeung, Sai-Kit, Global Context Aware Convolutions for 3D Point Cloud Understanding, International Conference on 3D Vision (3DV) 2020, 2020
Zhang, Zhiyuan and Hua, Binh-Son and Yeung, Sai-Kit, Shellnet: Efficient point cloud convolutional neural networks using concentric shells statistics, ICCV, 2019, pp1607--1616
Pham, Quang-Hieu and Nguyen, Duc Thanh and Hua, Binh-Son and Roig, Gemma and Yeung, Sai-Kit, JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields, CVPR, 2019
Hua, Binh-Son and Gruson, Adrien and Petitjean, Victor and Zwicker, Matthias and Nowrouzezahrai, Derek and Eisemann, Elmar and Hachisuka, Toshiya, A Survey on Gradient-Domain Rendering, Computer Graphics Forum, 38, (2), 2019, p455--472
Pham, Quang-Hieu and Hua, Binh-Son and Nguyen, Thanh and Yeung, Sai-Kit, Real-time progressive 3D semantic segmentation for indoor scenes, Winter Conference on Applications of Computer Vision (WACV), 2019, pp1089--1098
Zhang, Zhiyuan and Hua, Binh-Son and Rosen, David W and Yeung, Sai-Kit, Rotation invariant convolutions for 3d point clouds deep learning, 2019 International conference on 3d vision (3DV), 2019, pp204--213
Uy, Mikaela Angelina and Pham, Quang-Hieu and Hua, Binh-Son and Nguyen, Thanh and Yeung, Sai-Kit, Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data, ICCV, 2019, pp1588--1597
Ma, Rui and Patil, Akshay Gadi and Fisher, Matthew and Li, Manyi and Pirk, Soren and Hua, Binh-Son and Yeung, Sai-Kit and Tong, Xin and Guibas, Leonidas and Zhang, Hao, Language-driven synthesis of 3D scenes from scene databases, ACM Transactions on Graphics (TOG), 37, (6), 2018, p1--16
Hua, Binh-Son and Tran, Minh-Khoi and Yeung, Sai-Kit, Pointwise Convolutional Neural Networks, CVPR, 2018
Gruson, Adrien and Hua, Binh-Son and Vibert, Nicolas and Nowrouzezahrai, Derek and Hachisuka, Toshiya, Gradient-domain volumetric photon density estimation, ACM Transactions on Graphics (TOG), 37, (4), 2018, p1--13
Nguyen, Duc Thanh and Hua, Binh-Son and Yu, Lap-Fai and Yeung, Sai-Kit, A robust 3d-2d interactive tool for scene segmentation and annotation, TVCG, 2017
Hua, Binh-Son and Gruson, Adrien and Nowrouzezahrai, Derek and Hachisuka, Toshiya, Gradient-Domain Photon Density Estimation, Computer Graphics Forum, 2017
Nguyen, Duc Thanh and Hua, Binh-Son and Tran, Khoi and Pham, Quang-Hieu and Yeung, Sai-Kit, A field model for repairing 3d shapes, CVPR, 2016, pp5676--5684
Hua, Binh-Son and Pham, Quang-Hieu and Nguyen, Duc Thanh and Tran, Minh-Khoi and Yu, Lap-Fai and Yeung, Sai-Kit, SceneNN: A Scene Meshes Dataset with aNNotations, International Conference on 3D Vision (3DV), 2016, pp92--101
Hua, Binh-Son and Low, Kok-Lim, Guided path tracing using clustered virtual point lights, SIGGRAPH Asia 2015 Posters, 2015, pp1--1
Pahwa, Ramanpreet Singh and Do, Minh N and Ng, Tian Tsong and Hua, Binh-Son, Calibration of depth cameras using denoised depth images, 2014 IEEE International Conference on Image Processing (ICIP), 2014, pp3459--3463
Shen, Li and Yeo, Chuohao and Hua, Binh-Son, Intrinsic Image Decomposition Using a Sparse Representation of Reflectance, Transactions on Pattern Analysis and Machine Intelligence, 2013
Hua, Binh-Son and Ng, Tian-Tsong and Low, Kok-Lim, Reconstruction of Depth and Normals From Interreflections, Image Processing (ICIP), 2013 20th IEEE International Conference on, 2013, pp2557--2561
Hua, Binh-Son and Sato, Imari and Low, Kok-Lim, Direct and progressive reconstruction of dual photography images, 2013 IEEE International Conference on Image Processing, 2013, pp3157--3161
Hua, Binh-Son and Low, Kok-Lim, Interactive motion deblurring using light streaks, 2011 18th IEEE International Conference on Image Processing, 2011, pp1553--1556
Wang, Lei and Hua, Binh-Son and Li, Xueqing, Adaptive energy diffusion for blind inverse halftoning, Advances in Multimedia Information Processing-PCM 2010: 11th Pacific Rim Conference on Multimedia, Shanghai, China, September 21-24, 2010, Proceedings, Part I 11, 2010, pp470--480
Research Expertise
Projects
- Title
- Language3D: Creating Editable 3D Content from Deep Language Understanding for 3D-First Digital Platforms
- Summary
- This project aims to make 3D content accessible to everyone via developing new methods for automatic generation and manipulation of 3D content using machine intelligence. We take inspirations from large language models and investigate 3D content creation from deep language understanding. First, we propose to study the generation of photorealistic 3D content from text descriptions. This involves integrating photorealistic rendering techniques in computer graphics with text-to-3D generative models. Second, we propose to study pre-training of neural networks on 3D data, as inspired by the next-word prediction task for self-supervision in language models. This involves representing 3D models as a structured composition of 3D primitives and 3D parts and investigating self-supervised learning on these compositions. Third, we propose to study interactive 3D content generation via text guidance. The output of this project will encourage the creation of 3D-first platforms, where 3D data is accessible to everyone. The proposed techniques can benefit the growth of the metaverse and extended reality applications as well as different industries such as game development, film production, and architecture illustration. Language3D also contribute to future AI, where synthetic data can be created on a large scale from 3D content to train AI models with reduced cost.
- Funding Agency
- Research Ireland
- Date From
- 01-Aug-2024
- Date To
- 31-Jul-2028
- Title
- Physically based Generative Models for Visual Computing
- Funding Agency
- Enterprise Ireland
- Date From
- 21/06/2024
- Date To
- 20/06/2026
- Title
- Dojo3D: Building a Collaborative High-Performance Platform for Generative AI in 3D Visual Computing Research
- Funding Agency
- Higher Education Authority
- Title
- VISTA: Developing AI-Generated High-quality View Synthesis for Visual Computing Applications
- Funding Agency
- Dolby Laboratories
- Title
- SyntaGen: Harnessing Generative Models for Synthetic Visual Datasets
- Funding Agency
- Adobe, Inc
Recognition
Memberships
ELLIS Member (European Laboratories for Learning and Intelligent Systems)