Skip navigation
📢WorldAgents: 3D worlds only from 2D image models - without any training!
0:00 / 0:25

📢WorldAgents: 3D worlds only from 2D image models - without any training!

Matthias Niessner

@MattNiessner50K followers

Visit on X
268 likesDownloadOriginal post

19,093 views

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

4 Comments

Comments from the original post on X (Twitter)

  • Katja Schwarz's profile picture

    @K_S_Schwarz

    @ErkocZiya Our work [2503.16611] A Recipe for Generating 3D Worlds From a Single Image was among the first to show how to use image models like Flux to generate consistent worlds. You are missing the citation in the related work and attribution of credit.

    1 like

  • LionTV's profile picture

    @LionTV_crypto

    agents cooking 3D from 2D this is insane alpha drop

    1 like

  • Elon Orbit's profile picture

    @Elon_Orbit

    Director-Generator-Verifier pipeline. Solid. But anyone seen the compute bill? That's where these papers get quiet.

  • Jennifer Brauner's profile picture

    @Jenny3Brauner

    nice