UniQueR: Unified Query-based Feedforward 3D Reconstruction
📰 ArXiv cs.AI
UniQueR is a unified query-based feedforward framework for efficient and accurate 3D reconstruction from unposed images
Action Steps
- Formulate 3D reconstruction as a sparse query inference problem
- Learn a compact set of 3D anchors to represent the scene
- Use a feedforward network to predict 3D points and their corresponding occupancy probabilities
- Apply UniQueR to various applications such as robotics, autonomous driving, and augmented reality
Who Needs to Know This
Computer vision engineers and researchers on a team can benefit from UniQueR as it provides a novel approach to 3D reconstruction, and product managers can leverage this technology to develop innovative applications
Key Insight
💡 UniQueR formulates 3D reconstruction as a sparse 3D query inference problem, allowing for more accurate and efficient reconstruction
Share This
🔍 UniQueR: A novel query-based feedforward framework for 3D reconstruction from unposed images
Key Takeaways
UniQueR is a unified query-based feedforward framework for efficient and accurate 3D reconstruction from unposed images
Full Article
Title: UniQueR: Unified Query-based Feedforward 3D Reconstruction
Abstract:
arXiv:2603.22851v1 Announce Type: cross Abstract: We present UniQueR, a unified query-based feedforward framework for efficient and accurate 3D reconstruction from unposed images. Existing feedforward models such as DUSt3R, VGGT, and AnySplat typically predict per-pixel point maps or pixel-aligned Gaussians, which remain fundamentally 2.5D and limited to visible surfaces. In contrast, UniQueR formulates reconstruction as a sparse 3D query inference problem. Our model learns a compact set of 3D a
Abstract:
arXiv:2603.22851v1 Announce Type: cross Abstract: We present UniQueR, a unified query-based feedforward framework for efficient and accurate 3D reconstruction from unposed images. Existing feedforward models such as DUSt3R, VGGT, and AnySplat typically predict per-pixel point maps or pixel-aligned Gaussians, which remain fundamentally 2.5D and limited to visible surfaces. In contrast, UniQueR formulates reconstruction as a sparse 3D query inference problem. Our model learns a compact set of 3D a
DeepCamp AI