Junlin Han

Profile

Greetings, welcome to my website!

I am a researcher at GenAI research, Meta, and a second-year PhD (DPhil) student at the Torr Vision Group, University of Oxford, working with Prof. Philip Torr. Before that, I worked as a research scientist at Cybever, a 3D AIGC startup for a few months. I obtained my BSc from the Australian National University under the supervision of Dr. Lars Petersson, Prof. Hongdong Li, and Prof. Ian Reid.
I acknowledge that information asymmetry can significantly hinder research opportunities for junior students. If you’re interested in chatting about life, research, or potential collaborations, feel free to email me.
For undergrad and master's students at Oxford ONLY: If you are interested in an internship or 4YP at TVG working with me, please email me your current CV to discuss further. I usually take 1 or 2 interns per year and will provide some potential research ideas with hands-on guidance.

News

[05.2025] Flex3D was accepted to ICML 2025, a new two-stage pipeline for high-quality 3D generation and reconstruction!
[03.2025] One paper on point-cloud segmentation was accepted to CVPR 2025, congrats to Zhaochong!
[12.2024] Our previous work on low-level vision won the best paper award in Remote Sensing!
[12.2024] We will be organizing the 2nd Workshop on Foundation Models in the Wild at ICLR 2025!
[11.2024] Two papers (3D-GPT and DreamBeast) were accepted to 3DV 2025. Congratulations to Chunyi and Runjia! 3D-GPT is pioneering work in large-scale 3D scene generation, and DreamBeast is a fascinating project generating fantastical 3D animals.
[07.2024] VFusion3D and Unicorns were accepted to ECCV 2024! VFusion3D is the first work exploring scalable 3D generative/reconstruction models as a step towards a 3D foundation. Check it out if you are interested in 3D generation.
[04.2024] We are organizing ICML 2024 Foundation Models in the Wild Workshop, submissions on related topics are very welcomed!
[10.2023] Starting my PhD at Meta and Oxford!
[07.2023] Hyperbolic Audio-visual Zero-shot Learning was accepted to ICCV 2023!
[07.2023] Graduated from ANU with First-Class Honours.
[10.2022] Awarded as a top reviewer in NeurIPS 2022!
[07.2022] Blind Image Decomposition (BID) was accepted to ECCV 2022! A new low-level vision task that better adapts to complex real-world scenarios. Check our project page for more.
[05.2022] You Only Cut Once (YOCO) was accepted to ICML 2022! Check here for our work on how to perform data augmentation.
[12.2021] Joined Australian Institute for Machine Learning (AIML), University of Adelaide as a visiting research intern, hosted by Prof. Ian Reid!

Research Interests

My research focuses on the entire data lifecycle—from creation to utilization and understanding—to build more powerful and efficient AI systems, especially those that can actually work in very large-scale. My work is organized around three main topics, which you can click on to expand:

(1) Generation and manipulation of image, video, and 3D content,

Selected projects: Image decomposition, LLM for 3D scene generation, High-quality 3D asset generation

(2) Use augmented, synthetic, and curated data for training and scaling-up AI models,

Selected projects: How to perform data augmentation, Synthetic data for scaling-up 3D generative models

(3) Understand how data influences model's learning, decision-making, and emergent properties in order to build AI systems that scale predictably.

Selected projects: Memorability of images

Education

Postgraduate (01.2024 - ongoing)

PhD in Computer Vision, University of Oxford

Prof. Philip Torr

Undergraduate (02.2019 - 07.2023)

B.S. Information Technology (Honours), ANU

Dr. Lars Petersson

Prof. Hongdong Li

Prof. Ian Reid

Research Experience

PhD Student Researcher at GenAI, Meta (10.2023 - ongoing)

Topics: 3D&4D generation, Multimodal Large Language Models
Hosted by Dr. Filippos Kokkinos

Research Scientist, Cybever (05.2023 - 09.2023)

Topics: 3D generation

Visiting Research Intern at AIML, University of Adelaide (12.2021 - 05.2023)

Topics: Data-centric AI, Memorability
Advised by Prof. Ian Reid

Research Student at Data61-CSIRO & ANU (08.2020 - 05.2023)

Topics: Generative models, Self-supervised learning
Advised by Dr. Lars Petersson, Prof. Hongdong Li

Publications

Representative papers (as leading author) are highlighted.

Academic Services

Workshop Organization

Conference review

Journal review

Awards

Meta PhD Scholarship, 2023
for PhD research at University of Oxford
Best paper award, 2022
from Remote Sensing journal
Chancellor's Letter of Commendation, 2022
for best academic performance at Australian National University
Top Reviewer, 2022
NeurIPS (Conference on Neural Information Processing Systems)
Second Best Presentation Award, 2021
AIM (Active Integrated Matter) Conference
Top-up Scholarship, 2021
for research work at Data61-CSIRO
Undergraduate Vacation Scholarship, 2020
for summer research at Data61-CSIRO

Miscs

At the beginning, I was born and raised in Chengdu, which is famous for spice and pandas.
I studied and lived in China, Singapore, Australia, and UK.
Aside from research, I am passionate about traveling (especially nature travel), cooking, gaming, and swimming.