URoPE: Universal Relative Position Embedding across Geometric Spaces

• URL: http://arxiv.org/abs/2604.18747v1
• Date: Mon, 20 Apr 2026 18:52:03 GMT
• Title: URoPE: Universal Relative Position Embedding across Geometric Spaces
• Abstract summary: URoPE is a universal extension of Rotary Position Embedding (RoPE) to cross-view or cross-dimensional geometric spaces.<n>For each key/value image patch, URoPE samples 3D points along the corresponding camera ray at predefined depth anchors.<n>Standard 2D RoPE can then be applied using the projected pixel coordinates.
• Score: 55.651792747815854
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Relative position embedding has become a standard mechanism for encoding positional information in Transformers. However, existing formulations are typically limited to a fixed geometric space, namely 1D sequences or regular 2D/3D grids, which restricts their applicability to many computer vision tasks that require geometric reasoning across camera views or between 2D and 3D spaces. To address this limitation, we propose URoPE, a universal extension of Rotary Position Embedding (RoPE) to cross-view or cross-dimensional geometric spaces. For each key/value image patch, URoPE samples 3D points along the corresponding camera ray at predefined depth anchors and projects them into the query image plane. Standard 2D RoPE can then be applied using the projected pixel coordinates. URoPE is a parameter-free and intrinsics-aware relative position embedding that is invariant to the choice of global coordinate systems, while remaining fully compatible with existing RoPE-optimized attention kernels. We evaluate URoPE as a plug-in positional encoding for transformer architectures across a diverse set of tasks, including novel view synthesis, 3D object detection, object tracking, and depth estimation, covering 2D-2D, 2D-3D, and temporal scenarios. Experiments show that URoPE consistently improves the performance of transformer-based models across all tasks, demonstrating its effectiveness and generality for geometric reasoning. Our project website is: https://urope-pe.github.io/.

Related papers

• IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation [76.36174247570716]
  We propose IVGT, an Implicit Visual Geometry Transformer that implicitly models continuous and coherent geometry from pose-free multi-view images.<n> IVGT learns a continuous neural scene representation in a canonical coordinate system and supports continuous spatial queries at any 3D positions.<n>It allows direct extraction of continuous and coherent surface geometry, enabling rendering of RGB images, depth maps, and surface normal maps from arbitrary viewpoints.
  arXiv  Detail & Related papers  (2026-05-15T17:59:57Z)
• GeoPE:A Unified Geometric Positional Embedding for Structured Tensors [12.459742491179947]
  We introduce Geometric Positional Embedding (GeoPE), a framework that extends rotations to 3D Euclidean space using quaternions.<n>To overcome non-commutativity and ensure symmetry, GeoPE constructs a unified rotational operator by computing the geometric mean in the Lie algebra.<n>Experiments on image classification, object detection, and 3D semantic segmentation demonstrate that GeoPE consistently outperforms existing 2D RoPE variants.
  arXiv  Detail & Related papers  (2025-12-04T16:31:12Z)
• FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers [91.59069344768858]
  We introduce Frequency-aware Positional Depth Embedding (FreqPDE) to equip 2D image features with spatial information for 3D detection transformer decoder.<n>FreqPDE combines the 2D image features and 3D position embeddings to generate 3D depth-aware features for query decoding.
  arXiv  Detail & Related papers  (2025-10-17T07:36:54Z)
• WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting [51.69408870574092]
  We present WorldMirror, an all-in-one, feed-forward model for versatile 3D geometric prediction tasks.<n>Our framework flexibly integrates diverse geometric priors, including camera poses, intrinsics, and depth maps.<n>WorldMirror achieves state-of-the-art performance across diverse benchmarks from camera, point map, depth, and surface normal estimation to novel view synthesis.
  arXiv  Detail & Related papers  (2025-10-12T17:59:09Z)
• Tri-Perspective View Decomposition for Geometry-Aware Depth Completion [24.98850285904668]
  Tri-Perspective view Decomposition (TPVD) is a novel framework that can explicitly model 3D geometry. TPVD decomposes the original point cloud into three 2D views. TPVD outperforms existing methods on KITTI, NYUv2, and SUN RGBD.
  arXiv  Detail & Related papers  (2024-03-22T07:45:50Z)
• NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space [77.6067460464962]
  Monocular 3D Semantic Scene Completion (SSC) has garnered significant attention in recent years due to its potential to predict complex semantics and geometry shapes from a single image, requiring no 3D inputs. We identify several critical issues in current state-of-the-art methods, including the Feature Ambiguity of projected 2D features in the ray to the 3D space, the Pose Ambiguity of the 3D convolution, and the Imbalance in the 3D convolution across different depth levels. We devise a novel Normalized Device Coordinates scene completion network (NDC-Scene) that directly extends the 2
  arXiv  Detail & Related papers  (2023-09-26T02:09:52Z)
• CAPE: Camera View Position Embedding for Multi-View 3D Object Detection [100.02565745233247]
  Current query-based methods rely on global 3D position embeddings to learn the geometric correspondence between images and 3D space. We propose a novel method based on CAmera view Position Embedding, called CAPE. CAPE achieves state-of-the-art performance (61.0% NDS and 52.5% mAP) among all LiDAR-free methods on nuScenes dataset.
  arXiv  Detail & Related papers  (2023-03-17T18:59:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.