IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1

• URL: http://arxiv.org/abs/2603.19625v1
• Date: Fri, 20 Mar 2026 04:04:52 GMT
• Title: IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1
• Abstract summary: Relative pose estimation is fundamental for SLAM, visual localization, and 3D reconstruction.<n>Existing Relative Pose Regression (RPR) methods face a key trade-off: feature-matching pipelines achieve high accuracy but block gradient flow via non-differentiable RANSAC.<n>We propose IUP-Pose, a geometry-driven decoupled iterative framework with implicit dense alignment.
• Score: 4.987163446489143
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Relative pose estimation is fundamental for SLAM, visual localization, and 3D reconstruction. Existing Relative Pose Regression (RPR) methods face a key trade-off: feature-matching pipelines achieve high accuracy but block gradient flow via non-differentiable RANSAC, while ViT-based regressors are end-to-end trainable but prohibitively expensive for real-time deployment. We identify the core bottlenecks as the coupling between rotation and translation estimation and insufficient cross-view feature alignment. We propose IUP-Pose, a geometry-driven decoupled iterative framework with implicit dense alignment. A lightweight Multi-Head Bi-Cross Attention (MHBC) module aligns cross-view features without explicit matching supervision. The aligned features are processed by a decoupled rotation-translation pipeline: two shared-parameter rotation stages iteratively refine rotation with uncertainty, and feature maps are realigned via rotational homography H_inf before translation prediction. IUP-Pose achieves 73.3% AUC@20deg on MegaDepth1500 with full end-to-end differentiability, 70 FPS throughput, and only 37M parameters, demonstrating a favorable accuracy-efficiency trade-off for real-time edge deployment.

Related papers

• Robust structure from motion for aerial-ground images via detector-free feature matching and multi-view track refinement [15.28970239781579]
  Integrated 3D reconstruction from aerial-ground images is essential for generating high-precision urban 3D models.<n>This study introduces a rotation-robust detector-free matching network coupled with multi-view track refinement for incremental Structure from Motion (ISfM)<n>By using real aerial-ground datasets, experimental results demonstrate that the proposed method improves AUC at 5 pose error by 93.9% compared with LoFTR.
  arXiv  Detail & Related papers  (2026-08-15T14:16:02Z)
• ASTRA: Asynchronous Spatio-Temporal Reconstruction via Trajectory Alignment [86.35109211408489]
  We propose ASTRA, a framework that introduces 2D motion trajectories as explicit, texture-agnostic supervision for asynchronous dynamic reconstruction.<n>ASTRA preserves high-frequency spatial details and sustains strong robustness even under severe asynchrony with up to 25-frame offsets, achieving approximately 1.4 dB PSNR improvement, reducing temporal-offset MAE by 54.0%, and nearly quadrupling the synchronization success rate.
  arXiv  Detail & Related papers  (2026-08-03T10:06:45Z)
• SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry [69.89196162649091]
  SCOPE (Scale-Consistent One-Pass Estimation of 3D Geometry) is a novel approach for estimating 3D geometry from extended monocular video sequences.<n>Our approach generates affine-invariant 3D point maps with shared parameters across entire sequences, enabling consistent scale-invariant representations.
  arXiv  Detail & Related papers  (2026-06-19T10:23:25Z)
• MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons [56.68975315643491]
  We present the first fully end-to-end framework in which Videoto-Pose and Pose-to-Rotation are learnable and optimized jointly.<n>We show that our method reduces rotation error from 17 degrees to 10 degrees, and to 6.54 degrees on unseen skeletons, while achieving 20x faster inference than mesh-based pipelines.
  arXiv  Detail & Related papers  (2026-04-30T17:16:38Z)
• Unifying UAV Cross-View Geo-Localization via 3D Geometric Perception [51.687842983240564]
  Cross-view geo-localization for Unmanned Aerial Vehicles (UAVs) remains challenging due to the severe geometric discrepancy between oblique UAV imagery and satellite maps.<n>We propose a geometry-aware UAV geo-localization framework that explicitly models the 3D scene geometry to unify coarse place recognition and fine-grained pose estimation.<n>Our method significantly outperforms state-of-the-art baselines, achieving robust meter-level localization accuracy and improved generalization in complex urban environments.
  arXiv  Detail & Related papers  (2026-04-02T08:08:41Z)
• Bidirectional Feature-aligned Motion Transformation for Efficient Dynamic Point Cloud Compression [97.66080040613726]
  We propose a Bidirectional Feature-aligned Motion Transformation (Bi-FMT) framework that implicitly models motion in the feature space.<n>Bi-FMT aligns features across both past and future frames to produce temporally consistent latent representations.<n>We show Bi-FMT surpasses D-DPCC and AdaDPCC in both compression efficiency and runtime.
  arXiv  Detail & Related papers  (2025-09-18T03:51:06Z)
• H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction [39.22287224290769]
  H3R is a hybrid framework that integrates latent fusion with attention-based feature aggregation.<n>By integrating both paradigms, our approach enhances generalization while converging 2$times$ faster than existing methods.<n>Our method supports variable-number and high-resolution input views while demonstrating robust cross-dataset generalization.
  arXiv  Detail & Related papers  (2025-08-05T05:56:30Z)
• Bidirectional Regression for Monocular 6DoF Head Pose Estimation and Reference System Alignment [23.65735794927899]
  TRGv2 is a lightweight extension of our Translation, Rotation, and Geometry (TRG) network.<n>It infers facial landmarks and 6DoF pose through an iterative refinement loop with landmark-to-image projection.<n>To improve generalization to out-of-distribution data, TRGv2 regresses correction parameters instead of directly predicting translation.<n>We identify a previously overlooked source of bias in cross-dataset evaluations due to inconsistent head center definitions.
  arXiv  Detail & Related papers  (2024-07-19T09:05:49Z)
• An Accurate and Real-time Relative Pose Estimation from Triple Point-line Images by Decoupling Rotation and Translation [10.05584976985694]
  3D-2D constraints provided by line features have been widely used in Visual Odometry (VO) and Structure-from-Motion (SfM) systems.<n>We propose a novel three-view pose solver based on rotation-translation decoupled estimation.
  arXiv  Detail & Related papers  (2024-03-18T10:21:05Z)
• Rotation-Invariant Transformer for Point Cloud Matching [42.5714375149213]
  We introduce RoITr, a Rotation-Invariant Transformer to cope with the pose variations in the point cloud matching task. We propose a global transformer with rotation-invariant cross-frame spatial awareness learned by the self-attention mechanism. RoITr surpasses the existing methods by at least 13 and 5 percentage points in terms of Inlier Ratio and Registration Recall.
  arXiv  Detail & Related papers  (2023-03-14T20:55:27Z)
• DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets [95.84755169585492]
  We present Dynamic Sparse Voxel Transformer (DSVT), a single-stride window-based voxel Transformer backbone for outdoor 3D perception. Our model achieves state-of-the-art performance with a broad range of 3D perception tasks.
  arXiv  Detail & Related papers  (2023-01-15T09:31:58Z)
• DPCN++: Differentiable Phase Correlation Network for Versatile Pose Registration [18.60311260250232]
  We present a differentiable phase correlation solver that is globally convergent and correspondence-free. We evaluate DCPN++ on a wide range of registration tasks taking different input modalities, including 2D bird's-eye view images, 3D object and scene measurements, and medical images.
  arXiv  Detail & Related papers  (2022-06-12T10:00:34Z)
• Augmented Parallel-Pyramid Net for Attention Guided Pose-Estimation [90.28365183660438]
  This paper proposes an augmented parallel-pyramid net with attention partial module and differentiable auto-data augmentation. We define a new pose search space where the sequences of data augmentations are formulated as a trainable and operational CNN component. Notably, our method achieves the top-1 accuracy on the challenging COCO keypoint benchmark and the state-of-the-art results on the MPII datasets.
  arXiv  Detail & Related papers  (2020-03-17T03:52:17Z)
• Robust 6D Object Pose Estimation by Learning RGB-D Features [59.580366107770764]
  We propose a novel discrete-continuous formulation for rotation regression to resolve this local-optimum problem. We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction. Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-02-29T06:24:55Z)

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.