monocular-dynamic-reconstruction-is-hard-single-video-input-gt-a-lot-of-3d

Jonathon Luiten (@JonathonLuiten)

2025-06-25 | ❤️ 60 | 🔁 8

---

Monocular Dynamic Reconstruction is HARD!

Single video input –> A LOT of 3D ambiguity –> Significant visual artifacts.

BulletGen solves this using Generative Models, at various frozen ‘bullet-times’, fixing visual artifacts + filling-in missing info == much better results!

---

🔗 Related

See similar notes in domain-genai

인용 트윗

Denys Rozumnyi (@DRozumnyi)

Introducing 📢💥BulletGen: Improving 4D Reconstruction with Bullet-Time Generation

We improve 4D reconstruction from monocular videos by augmenting with bullet-time reconstructions form a generative model.

https://t.co/gQXVTTbEAK https://t.co/T9CSCINw9U https://t.co/8KWtfiTaCI

원본 트윗

🎬 영상

Tags

type-resource domain-genai