English

UniQueR: Unified Query-based Feedforward 3D Reconstruction

Computer Vision and Pattern Recognition 2026-03-25 v1 Artificial Intelligence

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 anchor points that act as explicit geometric queries, enabling the network to infer scene structure, including geometry in occluded regions--in a single forward pass. Each query encodes spatial and appearance priors directly in global 3D space (instead of per-frame camera space) and spawns a set of 3D Gaussians for differentiable rendering. By leveraging unified query interactions across multi-view features and a decoupled cross-attention design, UniQueR achieves strong geometric expressiveness while substantially reducing memory and computational cost. Experiments on Mip-NeRF 360 and VR-NeRF demonstrate that UniQueR surpasses state-of-the-art feedforward methods in both rendering quality and geometric accuracy, using an order of magnitude fewer primitives than dense alternatives.

Keywords

Cite

@article{arxiv.2603.22851,
  title  = {UniQueR: Unified Query-based Feedforward 3D Reconstruction},
  author = {Chensheng Peng and Quentin Herau and Jiezhi Yang and Yichen Xie and Yihan Hu and Wenzhao Zheng and Matthew Strong and Masayoshi Tomizuka and Wei Zhan},
  journal= {arXiv preprint arXiv:2603.22851},
  year   = {2026}
}
R2 v1 2026-07-01T11:34:53.647Z