no-nerf-no-3dgs-our-lvsm-delivers-state-of-the-art-view-synthesis-quality-from-s

Zexiang Xu (@zexiangxu)

2024-10-24 | ❤️ 89 | 🔁 16

---

No NeRF~ No 3DGS~ Our LVSM delivers state-of-the-art view synthesis quality from sparse-view inputs! Time to fully embrace scalable large transformers for building ‘3D-free’ 3D models and apps!

Amazing work by our intern @Haian_Jin and collaborators. 🔗https://haian-jin.github.io/projects/LVSM/

인용

[@Haian_Jin]: Novel view synthesis has long been a core challenge in 3D vision. But how much 3D inductive bias is truly needed? —Surprisingly, very little!

Introducing “LVSM: A Large View Synthesis Model with Mini…

---

인용 트윗

Haian Jin (@Haian_Jin)

Novel view synthesis has long been a core challenge in 3D vision. But how much 3D inductive bias is truly needed? —Surprisingly, very little!

Introducing “LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias”—a fully transformer-based approach that enables scalable, generalizable, and fully data-driven novel view synthesis, from sparse posed inputs. 🧵(1/6)

Project Page: https://t.co/Alqo3s0Qjt

원본 트윗

🎬 영상

Tags

domain-vision-3d domain-ai-ml