Changjian Li

Assistant Professor at the University of Edinburgh, my research interests are mainly Computer Graphics, 3D Computer Vision and Biomedical.

[Changjian Li @Enigmal_Li]

So proud of my student @LeiZhong_ for receiving the 2025 Google PhD Fellowship! His hard work and persistence have truly paid off — a well-deserved achievement!

[Google.org @Googleorg]

🎉 We're excited to announce the 2025 Google PhD Fellows! @GoogleOrg is providing over $10 million to support 255 PhD students across 35 countries, fostering the next generation of research talent to strengthen the global scientific landscape. Read more: https://t.co/0Pvuv6hsgP

[Changjian Li @Enigmal_Li]

@HaoLi81 @TheAcademy @PinscreenInc @mbzuai Congrats

[Changjian Li @Enigmal_Li]

Very glad that our Sketch2Anim (https://t.co/sbERqAiUTD) was selected as a technical paper highlight. Checkout our project page to know how we do this and more results.

[Hao (Richard) Zhang @richardzhangsfu]

A few #SIGGRAPH2025 papers on 3D generative AI being featured for press release:

https://t.co/noO3EwVTtK

See you all in Vancouver, August 10-14!

[Changjian Li @Enigmal_Li]

Thank for picking up our work. We have proposed a new method to enable trajectory control in the video diffusion model via simple 2d trajectory. Check out our paper for details. #CVPR2025

[naveen manwani @NaveenManwani17]

🚨CVPR 2025 Paper Alert 🚨

➡️Paper Title: PoseTraj: Pose-Aware Trajectory Control in Video Diffusion

🌟Few pointers from the paper

🎯Recent advancements in trajectory-guided video generation have achieved notable progress.

🎯However, existing models still face challenges in generating object motions with potentially changing 6D poses under wide-range rotations, due to limited 3D understanding.

🎯To address this problem, authors of this paper introduced “PoseTraj”, a pose-aware video dragging model for generating 3D-aligned motion from 2D trajectories.

🎯Their method adopts a novel two-stage pose-aware pretraining framework, improving 3D understanding across diverse trajectories.

🎯Specifically, they proposed a large-scale synthetic dataset PoseTraj-10K, containing 10k videos of objects following rotational trajectories, and enhance the model perception of object pose changes by incorporating 3D bounding boxes as intermediate supervision signals.

🎯Following this, they fine-tuned the trajectory-controlling module on real-world videos, applying an additional camera-disentanglement module to further refine motion accuracy.

🎯Experiments on various benchmark datasets demonstrate that their method not only excels in 3D pose-aligned dragging for rotational trajectories but also outperforms existing baselines in trajectory accuracy and video quality.

🏢Organization: @EdinburghUni , NTU

🧙Paper Authors: Longbin Ji,@LeiZhong_ , Pengfei Wei, @Enigmal_Li

📝 Read the Full Paper here: https://t.co/AnQJ3y2Tui

🗂️ Project Page: https://t.co/9pFpFuk6o9

🧑‍💻 Code: https://t.co/16VOLP3Ae2

🎥 Be sure to watch the attached Demo Video - Sound on 🔊🔊

Find this Valuable 💎 ?

♻️QT and teach your network something new

Follow me 👣, @NaveenManwani17 , for the latest updates on Tech and AI-related news, insightful research papers, and exciting announcements.

#CVPR2025

[Changjian Li @Enigmal_Li]

@amirvaxman_dgp Where are they?

[Changjian Li @Enigmal_Li]

#CVPR2024 - ContextSeg: Sketch Semantic Segmentation by Querying the Con... https://t.co/MbjFKXsFPe via @YouTube

Check out our ContextSeg for Sketch semantic segmentaton

[Changjian Li @Enigmal_Li]

cool

[Association for Computing Machinery @TheOfficialACM]

In this week's #PeopleofACM, we profile Adrien Bousseau, a Senior Researcher @Inria. Bousseau's interests include image creation and manipulation, shape modeling and scene understanding. Read the full interview here: https://t.co/mpwnj5govg
#computing #imagecreation #modeling

[Changjian Li @Enigmal_Li]

Reach out to us for this excited postdoc position

[Oisin Mac Aodha @oisinmacaodha]

What role does 3D have in learning robust representations of the visual world and can we develop scalable ways to inject 3D priors into our 2D self-supervised learning algorithms?

If you are interested in these questions, and looking for a postdoc position, please read on. #job

[Changjian Li @Enigmal_Li]

cool

[Hao Su @haosu_twitr]

📢Thrilled to announce sudoAI (@sudoAI_), founded by a group of leading AI talents and me!🚀

We are dedicated to revolutionizing digital & physical realms by crafting interactive AI-generated 3D environments!

Join our 3D Gen AI model waitlist today!
👉https://t.co/kBWdPXovkK

[Changjian Li @Enigmal_Li]

Investigation please

[Changjian Li @Enigmal_Li]

looks very cool, similar work is MVDream, it is good to read the two together

[Cheng Lin @_cheng_lin]

Super excited to share our #SyncDreamer! The most appealing part of this work is it can directly infer a number of multiview-consistent images from an arbitrary single image without the distillation (SDS) process.
Project page: https://t.co/2PeIuffwQW

[Changjian Li @Enigmal_Li]

Excited to submit

[Justin Solomon @JustinMSolomon]

Excited to share that the 2024 Symposium on Geometry Processing (SGP) @GeometryProcess will be at @MIT! This will be the first (non-virtual) SGP to be in North America. SGP is a premier venue for research in applied geometry, including fabrication, VR, 3D vision, & architecture.

[Changjian Li @Enigmal_Li]

Worth a good try

[Changjian Li @Enigmal_Li]

amazing

[Barsee 🐶 @heyBarsee]

Adobe released a new AI Feature in Photoshop 🤯

It makes Photoshop do magical things in seconds.

Here are 10 incredible use cases that are a game changer for creators:

[Changjian Li @Enigmal_Li]

crazy AI

[Barsee 🐶 @heyBarsee]

Another significant week for AI (with lots of new launch and crazy news)

Apple's new AI tool in works
Nvidia text-to-video
HuggingChat
The future of Browsing
Invisible Phones on user's hand
Russia's GIGAChat (ChatGPT rival)
Video to video on phones

Come and see 👇

[Changjian Li @Enigmal_Li]

Very happy to be part of the wonderful D3 project that is the ERC grant leads by Dr. Adrien Bousseau. Big congratulation! https://t.co/8DtbZp8C7N

[James Tompkin @jtompkin]

Are you a student researcher looking for their first pub🧑🏻‍🔬? Have late breaking work in graphics🐇or interaction👋? A neat smaller contribution🔬? Submit a two-page abstract to SIGGRAPH Posters https://t.co/MlGYGZuhIj - deadline in one week⌛- and celebrate the 50th with us!

[Changjian Li @Enigmal_Li]

@philipphenzler Congratulations !

[Changjian Li @Enigmal_Li]

@tunguz https://t.co/2WkkcCvqhf, I have done several work, check my webpage pls

[BITWU.ETH 🔆 @Bitwux]

🙏🙏🙏
身经百战，谈笑风生！
NAIVE, TOO YOUNG TOO SIMPLE！