Three ECCV 2026 acceptances turn 2D foundation models into 3D world-builders
angelaqdai · x · 2026-09-04
A team led by @ErkocZiya landed three papers at ECCV 2026:
- WorldAgents: an agentic approach turning 2D foundation models into 3D world-builders
- DreamEdit3D: 3D personalization for editing
- TriFlow (Long Oral): a novel mesh topology representation
The conference takes place in Malmö.
More from Multimodal
- Ant open-sources 5 Ming-3.0 speech models spanning TTS, audio understanding and ASR — Med1_Ai · 2026-10-21
- What keeps AI videos watchable: hooks, consistency and a payoff — aftahi_ai · 2026-10-21
- MORPHJUTSU skill in Flova transfers any video's motion to your character — aftahi_ai · 2026-10-21
- NVIDIA open-sources MotionBricks: 350K motion skills at 15,000 FPS, 2ms latency — aftahi_ai · 2026-10-21
- Runway joins Claude Marketplace, letting enterprises spend Anthropic budget on video generation — runwayml · 2026-10-21
- Kokon 0.10 turns Qwen-Image 2.1's text encoder into a prompt writer, no extra model — Ok-Director4174 · 2026-10-21