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

Original Tweet

---

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

• 1n-rotary-position-embeddings-rope-are-ubiquitous-across-tra — 주제: Reconstruction, Rope
• 1n-rotary-position-embeddings-rope-are-ubiquitous-across-transformers-that — 주제: Reconstruction, Rope
• eag-pt-emission-aware-gaussians-and-path-tracing-for-indoor—281012 — 주제: Reconstruction, Rope
• eag-pt-emission-aware-gaussians-and-path-tracing-for-indoor-scene-reconstruction — 주제: Reconstruction, Rope
• gr3en-generative-relighting-for-3d-environments-057299 — 주제: Reconstruction

Tags

3D-Vision AI-ML