SM4RT: Learning Structured Motion Geometry for 4D Reconstruction
- Published
- Source
- arXiv
- Paper number
- 720
- Field
- Computer Vision
- arXiv ID
- 2607.22534
Key points
- It proposes Structure-of-Motion, or SoM, a representation that expresses video motion as a combination of rigid motion bases rather than individual points.
- It infers 3D geometry, motion, and scene motion structure in a single forward pass.
- On the Kubric benchmark, it achieves state-of-the-art tracking accuracy, APD 90.62, and shows strong structure preservation on the deformation metric VM.
- The DA3 backbone outperforms VGGT by a wide margin, and simple linear fusion is the most effective feature fusion method.
- It is efficient at inference, taking 2.86 seconds per sample and using only 15.72 GB of GPU memory.
Paper links
External research summaries. These are not HDATF publications or measured product results.