Orest Kupyn

CV Researcher, Ukrainian 🇺🇦 | PhD Student at University of Oxford, Visual Geometry Group

[Letian Wang @Letian_Wang_6]

Can video generation models do for vision what LLMs did for language?

Introducing GenCeption from @GoogleDeepMind: one feed-forward video model for various vision tasks — SOTA, data-efficient, and emerging behaviors (ECCV 2026)

🌐 https://t.co/3rwVgTolZz

(1/8)

[Orest Kupyn @OKupyn]

@realsimon It’s open now

[Orest Kupyn @OKupyn]

📣New Paper: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation.
🌐 https://t.co/lvpmhTDLPB
🤗: https://t.co/AEvUNZtefY

A feedforward latent scene decoder for generating explicit triangle-based 3D scenes from video diffusion latents.

[Orest Kupyn @OKupyn]

@sammtmd @ZhaochongAn We can also have a chat anytime if you want 🙂

[Zhaochong An @ZhaochongAn]

Glad to see VGGRPO accepted to ECCV’26! Exciting times ahead🔥. See you all in Sweden!

[Orest Kupyn @OKupyn]

@taiyasaki Sure, we really appreciate the feedback! I think the current window function is still one of the main bottlenecks, so this should be an interesting experiment

[Orest Kupyn @OKupyn]

@janheld14 Thanks, wouldn’t be possible w/o Triangle and Mesh Splatting, thanks for your great work too!

[Orest Kupyn @OKupyn]

The final step is what makes the representation especially practical.
A lightweight test-time refinement turns the predicted triangle soup into a fully opaque, game-engine-ready asset that supports real-time rendering and direct physical interaction.

[Orest Kupyn @OKupyn]

Another nice property is flexibility.
FLAT is trained to decode video-model latents directly, so the same scene decoder can plug into Wan-2.1 style pipelines beyond a single mode, enabling text to 3D, image to 3D, real-time generation and others.

[Koichi Namekata @Koichi_N_]

Excited to share our #SIGGRAPH2026 paper: Go-with-the-Track!
We utilize point-tracks as spatiotemporal conditioning to precisely insert multiple reference images into generated videos.

Paper: https://t.co/gbBNilImRU
Project page: https://t.co/yB90SmOV7U

[Orest Kupyn @OKupyn]

Aggregated diffusion features also transfer beyond still images, including video-to-3D settings.
We hope this helps push toward more efficient multi-modal generation, where one model produces not just pixels, but richer complex outputs.

[Orest Kupyn @OKupyn]

Excited to release new paper: MMDiff: Extending Diffusion Transformers for Multi-Modal Generation
that was just accepted to #ECCV2026 and is finally out! 🎉

Project page 🌐: https://t.co/WAWbFqpLdD
Paper 📄: https://t.co/hbltDkB77N
Code: https://t.co/CwMOzWsF2n

[Orest Kupyn @OKupyn]

The key idea is multi-timestep feature aggregation.
Different denoising steps capture different parts of scene structure, so reading only the final latent leaves useful information behind. Aggregating across timesteps gives much stronger representations.

[Visual Geometry Group (VGG) @Oxford_VGG]

Congratulations to @ChuhanZhang5 @LiliMomeni @JunyuXieArthur Andrew and the team!! 🥳🥳

[Dmytro Mishkin 🇺🇦 @ducha_aiki]

Finally the orgs, who work for Russian government and helping developing weapon in the war of aggression against Ukraine have their papers desk rejected.
Thank you, @iclr_conf.
https://t.co/8vYtIUegRP