Jerred Chen

PhD student at @UniofOxford

[Jerred Chen @JerredChen]

@haofeixu @Mi_Niemeyer Yes it does! Thanks for the insightful answer :)

[Jerred Chen @JerredChen]

@haofeixu @Mi_Niemeyer Really great work!

Did you ever observe “blocky” artifacts from pixel-space prediction? From previous experiments with using an MLP decoder I’ve found that I couldn’t overcome that, so it’s amazing that your results are so clean.

[Ronnie Clark @ronnieclark__]

Introducing 𝗣𝗜𝗫𝗟𝗥𝗲𝗹𝗶𝗴𝗵𝘁 - our new method for precise image relighting. Our method allows you to specify the lighting you want exactly as in a standard 3D pipeline (no text prompts or exemplars).

Try the interactive demo here: https://t.co/xIA9Lvhp7g

w/Miguel Farinha

[Jacob Lin @jacob_lin2]

Interested in how 3D vision can help the development of high-resolution weather/climate models?

In our NeurIPS 2025 spotlight paper, we show how ground-based cameras can be used to estimate physically-meaningful 3D cloud properties at a high spatiotemporal resolution.

🧵 1/7

[Jerred Chen @JerredChen]

Now accepted in ICCV2025! See you in Hawaii 🌺

[Jerred Chen @JerredChen]

Motion blur typically breaks SLAM/SfM algorithms - but what if blur was actually the key to super-robust motion estimation?

In our new work, Image as an IMU, @ronnieclark__ and I demonstrate exactly how a single motion-blurred image can be used to our advantage.

🧵1/9

[Jerred Chen @JerredChen]

@ducha_aiki Thanks so much for sharing Dmytro! Really honored to make it as a post :,)

[Jerred Chen @JerredChen]

@lightchaserx @ducha_aiki Wow, that's a neat idea! Thanks for sharing 😃

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image

@JerredChen , Ronald Clark

tl;dr:predict flow from blurred image -> solve for velocity, use as IMU information.
https://t.co/9h7AKeBHOH

[Jerred Chen @JerredChen]

https://t.co/iin6qnDmTV

[Jerred Chen @JerredChen]

Motion blur typically breaks SLAM/SfM algorithms - but what if blur was actually the key to super-robust motion estimation?

In our new work, Image as an IMU, @ronnieclark__ and I demonstrate exactly how a single motion-blurred image can be used to our advantage.

🧵1/9

[Jerred Chen @JerredChen]

Thank you so much for posting our paper!

If you're interested in learning more, please see my explainer thread below:

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image

@JerredChen , Ronald Clark

tl;dr:predict flow from blurred image -> solve for velocity, use as IMU information.
https://t.co/9h7AKeBHOH

[Jerred Chen @JerredChen]

This project wouldn't have been possible without my supervisor @ronnieclark__ whose help and guidance I'm very grateful for, and thanks also to Linacre College and the CS Department for allowing us to use their spaces to record our test and training scenes.

9/9

[Jerred Chen @JerredChen]

Motion blur typically breaks SLAM/SfM algorithms - but what if blur was actually the key to super-robust motion estimation?

In our new work, Image as an IMU, @ronnieclark__ and I demonstrate exactly how a single motion-blurred image can be used to our advantage.

🧵1/9

[Jerred Chen @JerredChen]

For more details and results, please check out our paper and webpage!

arxiv: https://t.co/s6wffea8dn
webpage: https://t.co/bCEFyUFekf
8/9

[Jerred Chen @JerredChen]

@timmytan18 Thanks Tim