Xie et al., 'LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rende...

Kwang Moo Yi (@kwangmoo_yi)

2026-01-22 | ❤️ 81 | 🔁 6 | 💬 1

---

Xie et al., “LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models”

Cut3r latents adapted to be used together with Video DiT. 3D models seem to be quite useful for rendering things properly in 3D ;) https://x.com/kwangmoo_yi/status/2014434012492923111/video/1

🔗 원본 링크

• https://x.com/kwangmoo_yi/status/2014434012492923111/video/1

미디어

---

🔗 Related

• transforms-a-simple-3d-scene-into-a-realistic-render-and-is — 주제: Rendering, Vision/3D, GenAI
• if-youve-ever-tried-to-create-3dgs-scenes-from-photos-taken — 주제: Rendering, AI-ML, Vision/3D
• luxremix-lighting-decomposition-and-remixing-for-indoor — 주제: Rendering, AI-ML, Vision/3D
• you-could-direct-a-video-like-a-real-3d-world-researchers — 주제: Vision/3D, AI-ML, GenAI
• exciting-new-work-on-detailed-pixel-level-dense-3d-visual — 주제: Vision/3D, AI-ML, GenAI

Tags

Vision-3D Rendering GenAI AI-ML