About Me
I am a D.Phil. candidate in Computer Science at the University of Oxford, co-supervised by Profs. Niki Trigoni and Andrew Markham. My study is generously supported by the Taiwanese Government Scholarship to Study Abroad, ACE-OPS grant, and St. Catherine’s College Overseas Scholarship.
I also had the privilege of collaborating closely with Matheus Gadelha, Thibault Groueix, Matthew Fisher, Soren Pirk, and Radomir Mech during my internships at Adobe Research, and Varun Jampani, Prafull Sharma, and Mark Boss during my internship at Stability AI. Prior to my D.Phil., I worked as a research assistant in Computer Vision Lab, Academia Sinica, supervised by Profs. Tyng-Luh Liu and Hwann-Tzong Chen.
I plan on submitting my thesis in the coming months and will soon be entering the job market. Feel free to contact me for any research opportunities!
Research Interests
My main research interest lies on bridging 2D and 3D Understanding. My D.Phil. work mainly builds on extracting 3D information in the latent space from large image collections to enhance the capabilities of models for generation and reconstruction. So far, I have worked on extracting geometry (3DMiner), illumination and deformable shape changes (Continuous 3D Words), and more recently materials (ZeST).
On the side, I also enjoy working with vision applications that utilize various modalities, such as point clouds and thermal images.
News
- [Jul. 2024] Many news in July! I started a internship at Adobe Research London (Mentors: Chun-Hao Huang, Duygu Ceylan), I defended my Confirmation viva (Examiners: Prof. Christian Rupprecht, Prof. Ronald Clark), and our paper ZeST got accepted into ECCV 2024!
- [Mar. 2024] Started a part-time internship at Stability AI! (Mentors: Varun Jampani, Mark Boss)
- [Feb. 2024] Our paper Continuous 3D Words got accepted into CVPR 2024! Check out our work here!
- [Sep. 2023] Our paper on Multi-Body SE(3) Equivariance is accepted to NeurIPS 2023!
- [Aug. 2023] Three papers are accepted to IEEE Transactions on Intelligent Transportation Systems, WACV 2024, and BMVC 2024.
- [Jul. 2023] Our paper 3DMiner got accepted into ICCV 2023!
- [May. 2023] Started my second internship at Adobe Research! (Mentors: Matheus Gadelha, Thibault Groueix, Matthew Fisher, and Radomir Mech)
- [Dec. 2022] Defended my Transfer of Status viva (Examiners: Prof. Yarin Gal, Prof. Ronald Clark).
- [Jul. 2022] Our paper Meta-Sampler got accepted into ECCV 2022!
- [Jun. 2022] Started my internship at Adobe Research! (Mentors: Matheus Gadelha, Soren Pirk, Thibault Groueix, and Radomir Mech)
- [Dec. 2021] Our paper PADMix got accepted into AAAI 2022!
- [Oct. 2021] Started my D.Phil. journey at the University of Oxford.
Selected Publications (Full list on Google Scholar)
-
ECCV
ZeST: Zero-Shot Material Transfer from a Single Image
Ta-Ying Cheng, Prafull Sharma, Andrew Markham, Niki Trigoni, Varun Jampani
European Conference on Computer Vision (ECCV), 2024.
ArXiv
Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition
Chun-Hsiao Yeh*, Ta-Ying Cheng*, He-Yen Hsieh*, Chuan-En Lin, Yi Ma, Andrew Markham, Niki Trigoni, H.T. Kung, Yubei Chen (*=Equal Contribution)
ArXiv, 2024.
CVPR
Learning Continuous 3D Words for Text-to-Image Generation
Ta-Ying Cheng, Matheus Gadelha, Thibault Groueix, Matthew Fisher, Radomir Mech, Andrew Markham, Niki Trigoni
Computer Vision and Pattern Recognition (CVPR), 2024.
ICCV
3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets
Ta-Ying Cheng, Matheus Gadelha, Soren Pirk, Thibault Groueix, Radomir Mech, Andrew Markham, Niki Trigoni
International Conference on Computer Vision (ICCV), 2023.
ECCV
Meta-Sampler: Almost-Univsersal yet Task-Oriented Sampling for Point Clouds
Ta-Ying Cheng, Qingyong Hu, Qian Xie, Niki Trigoni, Andrew Markham
European Conference on Computer Vision (ECCV), 2022.
AAAI
Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction
Ta-Ying Cheng*, Hsuan-Ru Yang*, Niki Trigoni, Hwann-Tzong Chen, Tyng-Luh Liu (*=Equal Contribution)
AAAI Conference on Artifical Intelligence, 2022.
CHI
ARchitect: Building Interactive Virtual Experiences from Physical Affordances by Bringing Human-in-the-Loop
Chuan-En Lin*, Ta-Ying Cheng*, Xiaojuan Ma (*=Equal Contribution)
CHI Conference on Human Factors in Computing Systems, 2020.
Services
Conference Reviewers
Powered by Jekyll and Minimal Light theme.