Computer Vision Research Scientist at @simulon, music lover , fond of scientific/musical/geeky/useless stuff. I'm posting papers on whatever I found amazing :)
Paris, France
Joined June 2012
- Tweets3.2K
- Following308
- Followers2.4K
- Likes4.5K
"PixGR: Pixel-Space Generative Decoding for Fast Feed-Forward 3D Reconstruction"
TL;DR: combines pixel-space flow matching with feed-forward 3D Gaussian reconstruction, improving geometry and appearance in unseen regions while maintaining sub-second inference.
Ranran Huang¹, @wenjing_bian², Weixun Luo¹, Ye Mao¹, Krystian Mikolajczyk¹
¹ @imperialcollege
² @uni_tue
Project page: ranrhuang.github.io/pixgr/
Paper: arxiv.org/abs/2610.31908
Code: github.com/ranrhuang/PixGR (coming soon)
Alexandre Morgand retweeted
In @Simulon, you can turn any image into a 3D neural asset and bring it into the real world.
Dracula started as a single image. A minute later, he’s riding a real RC car across my dining table, with his cape swinging through the turns. When the car goes over the edge, he jumps off the car and stays on the table.
All of this happens procedurally, with no prompting. He responds to the space and what’s happening around him. The inset shows the original footage.
What would you bring into the world? Drop an image in the replies and tell me what you’d like to see it do. I’ll pick a few and bring your ideas to life.
Video generation is not new but at @Simulon the keyword was always about control. How do you navigate through vfx with the least friction possible? How do you maximise creativity? Impossible question but I think a path of the answer is here!
Introducing Reality-Aware Rendering in @Simulon, a completely new way to create with the real world.
Place neural assets with your phone and act out the scene. When you stop recording, Simulon renders the take, reading everything in it (what you do, what you say and the place around you), and your assets respond to all of it.
The final is regenerated from your recording: a new performance of the scene, not a copy of the footage.
Available now on iPhone. Coming to Android soon.
Alexandre Morgand retweeted
Check out this Reality-Aware rendering feature from the new @Simulon 2.0. This is a game changer.
Introducing Reality-Aware Rendering in @Simulon, a completely new way to create with the real world.
Place neural assets with your phone and act out the scene. When you stop recording, Simulon renders the take, reading everything in it (what you do, what you say and the place around you), and your assets respond to all of it.
The final is regenerated from your recording: a new performance of the scene, not a copy of the footage.
Available now on iPhone. Coming to Android soon.
Alexandre Morgand retweeted
Introducing Reality-Aware Rendering in @Simulon, a completely new way to create with the real world.
Place neural assets with your phone and act out the scene. When you stop recording, Simulon renders the take, reading everything in it (what you do, what you say and the place around you), and your assets respond to all of it.
The final is regenerated from your recording: a new performance of the scene, not a copy of the footage.
Available now on iPhone. Coming to Android soon.
Basically, if you want to save money, just do close up shots. Seedance2.5 still better overall imo (as well).
Shoutout @jon_barron for the whole thing + nice visuals and @jbhuang0604 for the video on it! youtu.be/dYxEmKbZfr4?si=FyXG… (worthy subscription!)
"FoundationVIO: Enforcing Metric Scale in Feed-forward Visual-Inertial Odometry"
TLDR: 3D foundation models + IMU measurements and factor-graph optimization to recover metric-scale camera trajectories and dense 3D reconstructions, with loop closure for globally consistent SLAM.
Jin Rhee¹, Yuhao Zhang¹, @fdellaert², @MauriceFallon¹
¹ Oxford Robotics Institute, @UniofOxford
² School of Interactive Computing, @GeorgiaTech
Project page: dynamic.robots.ox.ac.uk/proj…
Paper: arxiv.org/abs/2610.14951
Code: github.com/ori-drs/Foundatio…
"PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training"
TLDR: improves VGGT, Pi3, and DA3 using unlabeled video post-training, combining relative depth constraints, local geometry distillation, and correspondence-based pose refinement 1/2
to produce more accurate and temporally consistent 3D reconstructions of dynamic scenes without additional inference overhead. 2/2
Project page: funnyguy525.github.io/PURE-P…
Paper: arxiv.org/abs/2610.14698
Code: github.com/IGL-HKUST/PURE
Demo: huggingface.co/spaces/cyun92…
One year ago, I would have never imagined that we could reach this level of Mixed Reality with complex interactions. This is an incredible achievement at @Simulon but you would be surprised by how easy it is to use! Give it a try! (Android version is launching soon!)
Here’s how @Simulon Reality-Aware Rendering works. I placed my raptor next to the water and dropped a stone in to see how he’d respond.
His 3D placement sets his starting position and scale. When the recording starts, he becomes a ghost, leaving me to shape the performance through actions, gestures and spoken instructions. Simulon uses the recorded scene to generate his behaviour and integrate him into the footage afterward.
Instead of typing a prompt, spinning the slot machine and hoping for the best, you can show it, say it and perform it. Your intent, timing and spatial context are right there in the recording. It’s a much more intuitive way to create.
This breakdown is generated procedurally, summarising the actual reasoning behind the result.