Introducing ShapeR, a method for robust conditional 3D shape generation from cas...

Yawar Siddiqui (@yawarnihal)

2026-01-19 | ❤️ 1015 | 🔁 145 | 💬 18

---

Introducing ShapeR, a method for robust conditional 3D shape generation from casually captured sequences.

ShapeR leverages a rectified flow transformer conditioned on per-object multimodal data to turn casual image sequences into full metric scene reconstructions.

Project Page: https://facebookresearch.github.io/ShapeR/ Paper: https://arxiv.org/abs/2601.11514

Links to code and huggingface below ⬇️

🔗 원본 링크

• https://facebookresearch.github.io/ShapeR/
• https://arxiv.org/abs/2601.11514

미디어

---

🔗 Related

• you-could-direct-a-video-like-a-real-3d-world-researchers — 주제: AI-ML, Dev-Tools, Vision/3D
• why-does-llm-generated-code-still-fail-to-compile-or-run — 주제: AI-ML, Dev-Tools, Vision/3D
• thinking-with-blender-meet-viga-a-multimodal-agent-that — 주제: AI-ML, Dev-Tools, Vision/3D
• what-if-we-could-model-vision-like-a-wave-moving-through — 주제: AI-ML, Dev-Tools
• what-if-sim-and-reality-were-one-this-system-keeps-them-in — 주제: AI-ML, Vision/3D

Tags

Vision-3D AI-ML Dev-Tools