Sotiris Nousias

📢 Generative View Stitching! We worked with @ndsong95 to tame the short scope of view conditioned video models. Auto-regressive sampling extends the duration of generated videos but collapse when they are camera conditioned. Check how we solved it on our new paper. andrewsonga.github.io/gvs/

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: research.nvidia.com/labs/toronto-a… Code and Models: github.com/nv-tlabs/lyra Paper: arxiv.org/abs/2509.19296

Every lens leaves a blur signature—a hidden fingerprint in every photo. In our new #TPAMI paper, we show how to learn it fast (5 mins of capture!) with Lens Blur Fields ✨ With it, we can tell apart ‘identical’ phones by their optics, deblur images, and render realistic blurs.

Checkout this episode of the @executive_code for a dive into our work on modeling light propagation!

Come see @megatran23 present our work on MeCapture at #SIGGRAPH2025 appy hour! Based on our UIST2024 paper with @ethane_yang and @lique_taylor.

🚀 Just published in Nature Photonics: synthetic aperture waveguide holography—a new path toward ultra-thin, high-quality 3D mixed reality displays. 📄 nature.com/articles/s4156… #Photonics #Holography #MR 1/5

Happy to have led local arrangements for #ICCP2025! Massive thanks to our volunteers for making it possible: @Dongyu_Du, @andrewyguo, Len Luong, Ali SaraerToosi, Howard Xiao, @AndrewEJXie, Sophia Yang, and @KellyKZhu! And, @Sotiris_No and Jazmin Diaz for being the best co-chairs!

@ICCP_conference well deserved drinks after a great day of talks 📸🤗🍻

📸 Join us at ICCV 2025 for our workshop on Computer Vision with Single-Photon Cameras (CVSPC)! 🗓️  Sunday, Oct 19, AM – PM at the Hawai'i Convention Center. 🔗 Website: cvspc.cs.pdx.edu. 🗣️ Invited Speakers: Mohit Gupta, @mpotoole, @Dongyu_Du, @DaveLindell, @adaveiitm. 📍Submit your poster and join the conversation! We welcome early ideas & in-progress work. 📝 Poster submission form: lnkd.in/gY5yMypc. 🏆 Stay tuned for a CVSPC competition announcement! 👥 Thanks to co-organizers: Atul Ingle, Mel White, Mian Wei and Sacha Jungerman! @ICCVConference

📣📣📣 Neural Inverse Rendering from Propagating Light 💡 just won Best Student Paper award at #CVPR!!!

@adaveiitm @stonybrooku Huge congratulations @adaveiitm !!!!

📢 I'm happy to share that I'll be joining @stonybrooku as an Assistant Professor in CS this Fall. I will start the Photon Intelligence Lab, developing physics-aware AI that sees what we cannot – by bridging optics, graphics, and vision. Come join us! DM or meet me @ CVPR 🧵👇

📢Excited to be at #ICLR2025 for our paper: VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control Poster: Thu 3-5:30 PM (#134) Website: snap-research.github.io/vd3d/ Code: github.com/snap-research/… Also check out our #CVPR2025 follow-up AC3D: snap-research.github.io/ac3d/

MambaTM is our latest image restoration method for atmospheric turbulence To appear @CVPR 2025 (Highlight paper 13.5%) arxiv.org/abs/2504.02697 - Learned phase distortion in the loop - Mamba state-space model for speed All credits to Xingguang Zhang @PurdueECE

Happy to share that 🧢CAP4D🧢 has been accepted to CVPR 2025 (Oral)! Looking forward to seeing you all in Nashville 🎉

@gkopanas @runwayml 🎉🎉🎉🎉 exciting!!!!

Small life update: Just joined @runwayml , quite excited to work on video models and figure out tools for creative artists in the modern era.

I will be in Tokyo this week for #SiggraphAsia2024 to present our work "Coherent Optical Modems for Full-Wavefield Lidar". We repurposed an off-the-shelf optical modem, typically used for telecommunications, to introduce Full-Wavefield Lidar: a new imaging modality for simultaneous measurement of mm-scale 3D geometry, velocity, and polarization with only 1 microsecond exposure at eye-safe power regime. 📜 Paper: arxiv.org/abs/2406.08439 🌐 Project Webpage: dgp.toronto.edu/fullwavefieldl… Joint work with @LightIsMyGame, @maxx_wu, Doug Charlton, Mohammad Pasandi, @kyroskutulakos, and @DaveLindell. (1/4)

I am on the job market, seeking tenure-track or industry research positions starting in 2025. My research combines human-computer interaction and robotics—please visit karthikmahadevan.ca for updated publications and CV. Feel free to reach out if interested. RT appreciated!

@tzoumpekas @acia_cat Congrats!!!!

A bit late, but excited to share that I defended my PhD thesis this summer with Excellent - Cum Laude distinction and received the Award "Premi Marc Esteva Vivanco 2024" for the Best Doctoral Thesis in #AI from the Catalan Association of AI (@acia_cat)! 🎉🎇 #PhD #AI #CV #ML

At #ECCV2024, we presented Minimalist Vision with Freeform Pixels, a new vision paradigm that uses a small number of freeform pixels to solve lightweight vision tasks. We are honored to have received the Best Paper Award! Check out the project here: cave.cs.columbia.edu/projects/categ…