InfiniDream: VLM-Driven Procedural Generation of Open-Ended Photorealistic 3D Worlds
AlayaLab · hf · 2026-10-20
Alaya Lab, NYCU and NTU introduce InfiniDream, a VLM-driven framework for open-ended procedural 3D world generation, with code open-sourced.
- Symbolically constrained asset generation reuses existing procedural algorithms to create novel photorealistic assets while preserving editability and seed-based diversity
- An end-to-end text-to-world pipeline combines semantic scene planning with deterministic frustum-guided grid placement for precise object placement, procedural population, and animation
- Evaluated on 100 object and 20 scene generation tasks, showing gains across four perceptual metrics, validated by diversity analysis, ablations, and human preference studies
More from Multimodal
- MOSS Image with 8-step Turbo LoRA tested: 10x faster with minimal quality loss — Aggressive_Collar135 · 2026-10-20
- User turns their AI muse Maki into a punky ska song with Suno V6 — thederbiedone · 2026-10-20
- Grok Imagine parody short 'Wendy' shows off AI-made TV skits — Old_Put1306 · 2026-10-20
- AI-generated "Back to the Future" sequel clip goes viral for Halloween — mitchdeg · 2026-10-20
- Midjourney v8.2 style ref 1631327937 yields a dreamy pastel look — azed_ai · 2026-10-20
- Google Flow hosts hybrid production workshop pairing live-action with AI filmmaking workflows — lmoroney · 2026-10-20