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

Original Tweet

---

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

• introducing-360anything-our-method-for-lifting-any-perspecti — 주제: Panorama, Reconstruction, Transformer
• introducing-360anything-our-method-for-lifting-any-perspective-image-or-video-to — 주제: Panorama, Reconstruction, Transformer
• 1n-rotary-position-embeddings-rope-are-ubiquitous-across-tra — 주제: Reconstruction, Transformer
• 1n-rotary-position-embeddings-rope-are-ubiquitous-across-transformers-that — 주제: Reconstruction, Transformer
• iggt-instance-grounded-geometry-transformer — 주제: Reconstruction, Transformer

Tags

3D-Vision AI-ML