GeLoc3r: Enhancing Relative Camera Pose Regression with Geometric Consistency Regularization

• URL: http://arxiv.org/abs/2509.23038v1
• Date: Sat, 27 Sep 2025 01:21:38 GMT
• Title: GeLoc3r: Enhancing Relative Camera Pose Regression with Geometric Consistency Regularization
• Abstract summary: Prior ReLoc3R achieves breakthrough performance with fast 25ms inference and state-of-the-art regression accuracy.<n>We present GeLoc3r, a novel approach to relative camera pose estimation that enhances pose regression methods through geometric consistency regularization.
• Score: 44.00455492098006
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Prior ReLoc3R achieves breakthrough performance with fast 25ms inference and state-of-the-art regression accuracy, yet our analysis reveals subtle geometric inconsistencies in its internal representations that prevent reaching the precision ceiling of correspondence-based methods like MASt3R (which require 300ms per pair). In this work, we present GeLoc3r, a novel approach to relative camera pose estimation that enhances pose regression methods through Geometric Consistency Regularization (GCR). GeLoc3r overcomes the speed-accuracy dilemma by training regression networks to produce geometrically consistent poses without inference-time geometric computation. During training, GeLoc3r leverages ground-truth depth to generate dense 3D-2D correspondences, weights them using a FusionTransformer that learns correspondence importance, and computes geometrically-consistent poses via weighted RANSAC. This creates a consistency loss that transfers geometric knowledge into the regression network. Unlike FAR method which requires both regression and geometric solving at inference, GeLoc3r only uses the enhanced regression head at test time, maintaining ReLoc3R's fast speed and approaching MASt3R's high accuracy. On challenging benchmarks, GeLoc3r consistently outperforms ReLoc3R, achieving significant improvements including 40.45% vs. 34.85% AUC@5{\deg} on the CO3Dv2 dataset (16% relative improvement), 68.66% vs. 66.70% AUC@5{\deg} on RealEstate10K, and 50.45% vs. 49.60% on MegaDepth1500. By teaching geometric consistency during training rather than enforcing it at inference, GeLoc3r represents a paradigm shift in how neural networks learn camera geometry, achieving both the speed of regression and the geometric understanding of correspondence methods.

Related papers

• RIDE: Relocalization-Informed Depth Estimation with 3D Gaussian Splatting [20.29273985020268]
  We present RIDE, which estimates dense depth from a robot's RGB map.<n>Experiments show improved depth accuracy temporal consistency scale-only calibration, demonstrating how dense geometry can support both pose recovery and robot perception.
  arXiv  Detail & Related papers  (2026-09-10T04:36:58Z)
• GeoWeaver: Accurate Long-Sequence 3D Reconstruction via Hierarchical Geometric Assembly [23.486108847409856]
  Long-sequence 3D reconstruction from RGB videos requires both accurate local geometry and globally consistent camera motion.<n>We present GeoWeaver, a unified framework comprising a Geometric Prior Model (GPM) and Test-Time Adaptation (TTA)<n>TTA performs sequential, global chunk-level Sim(3) alignment, and coarse-to-fine refinement of camera poses, affine depth corrections, and intrinsics.<n> Experiments across diverse long-sequence benchmarks demonstrate improved camera accuracy, global consistency, and point-cloud quality.
  arXiv  Detail & Related papers  (2026-08-18T05:29:31Z)
• Geometric Context Transformer for Streaming 3D Reconstruction [51.19524805829903]
  LingBot-Map is a feed-forward 3D foundation model for reconstructing scenes from streaming data.<n>A defining aspect of LingBot-Map lies in its carefully designed attention mechanism, which integrates an anchor context, a pose-reference window, and a trajectory memory.<n>This design keeps the streaming state compact while retaining rich geometric context, enabling stable efficient inference at around 20 FPS on 518 x 378 resolution inputs.
  arXiv  Detail & Related papers  (2026-04-15T17:58:13Z)
• Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction [50.5449251266956]
  This paper addresses the task of large-scale 3D scene reconstruction from long video sequences.<n>Recent feed-forward reconstruction models have shown promising results by directly regressing 3D geometry from RGB images without explicit 3D priors or geometric constraints.<n>We propose a novel neural global context representation that efficiently compresses and retains long-range scene information.
  arXiv  Detail & Related papers  (2026-04-09T17:59:50Z)
• Do Foundation Models Know Geometry? Probing Frozen Features for Continuous Physical Measurement [0.0]
  Vision-language models encode geometry that their text pathway fails to express.<n>LoRA fine-tuning (r=16, 2,000 images) narrows this gap to 6.5 degrees.<n>These findings enable a single frozen backbone to function as a multi-task geometric sensor.
  arXiv  Detail & Related papers  (2026-03-06T16:48:27Z)
• Curvature-Regularized Variational Autoencoder for 3D Scene Reconstruction from Sparse Depth [0.0]
  We propose curvature regularization through a discrete Laplacian operator, achieving 18.1% better reconstruction accuracy than standard variational autoencoders.<n>Our contribution challenges an implicit assumption in geometric deep learning: that combining multiple geometric constraints improves performance.
  arXiv  Detail & Related papers  (2025-12-05T15:11:04Z)
• GRLoc: Geometric Representation Regression for Visual Localization [14.972457710617816]
  Absolute Pose Regression has emerged as a compelling paradigm for visual localization.<n>In this work, we propose a geometrically-grounded alternative.<n>We demonstrate state-of-the-art performance on 7-Scenes and Cambridge Landmarks datasets.
  arXiv  Detail & Related papers  (2025-11-17T19:30:22Z)
• Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline [64.42938561167402]
  We propose an online 3D reconstruction method using 3D Gaussian-based SLAM, combined with a feed-forward recurrent prediction module.<n>This approach replaces slow test-time optimization with fast network inference, significantly improving tracking speed.<n>Our method achieves performance on par with the state-of-the-art SplaTAM, while reducing tracking time by more than 90%.
  arXiv  Detail & Related papers  (2025-08-06T16:16:58Z)
• Dens3R: A Foundation Model for 3D Geometry Prediction [44.13431776180547]
  Dens3R is a 3D foundation model designed for joint geometric dense prediction.<n>By integrating image-pair matching features with intrinsic invariance modeling, Dens3R accurately regresses multiple geometric quantities.
  arXiv  Detail & Related papers  (2025-07-22T07:22:30Z)
• Test3R: Learning to Reconstruct 3D at Test Time [58.0912500917036]
  Test3R is a surprisingly simple test-time learning technique that significantly boosts geometric accuracy.<n>Our technique significantly outperforms previous state-of-the-art methods on the 3D reconstruction and multi-view depth estimation tasks.
  arXiv  Detail & Related papers  (2025-06-16T17:56:22Z)
• 3D Face Reconstruction Error Decomposed: A Modular Benchmark for Fair and Fast Method Evaluation [30.625439879741847]
  We present a toolkit for a Modularized 3D Face reconstruction Benchmark (M3DFB)<n>The fundamental components of error are segregated and interchangeable, allowing one to quantify the effect of each.<n>We propose a new component, namely correction, and present a computationally efficient approach that penalizes for mesh topology inconsistency.
  arXiv  Detail & Related papers  (2025-05-23T15:28:43Z)
• Speedy MASt3R [68.47052557089631]
  MASt3R redefines image matching as a 3D task by leveraging DUSt3R and introducing a fast reciprocal matching scheme.<n>Fast MASt3R achieves a 54% reduction in inference time (198 ms to 91 ms per image pair) without sacrificing accuracy.<n>This advancement enables real-time 3D understanding, benefiting applications like mixed reality navigation and large-scale 3D scene reconstruction.
  arXiv  Detail & Related papers  (2025-03-13T03:56:22Z)
• CDGS: Confidence-Aware Depth Regularization for 3D Gaussian Splatting [5.8678184183132265]
  CDGS is a confidence-aware depth regularization approach developed to enhance 3DGS.<n>We leverage multi-cue confidence maps of monocular depth estimation and sparse Structure-from-Motion depth to adaptively adjust depth supervision.<n>Our method demonstrates improved geometric detail preservation in early training stages and achieves competitive performance in both NVS quality and geometric accuracy.
  arXiv  Detail & Related papers  (2025-02-20T16:12:13Z)
• FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models [67.96827539201071]
  We propose a novel test-time optimization approach for 3D scene reconstruction. Our method achieves state-of-the-art cross-dataset reconstruction on five zero-shot testing datasets.
  arXiv  Detail & Related papers  (2023-08-10T17:55:02Z)
• Neural Refinement for Absolute Pose Regression with Feature Synthesis [33.2608395824548]
  Absolute Pose Regression (APR) methods use deep neural networks to directly regress camera poses from RGB images. In this work, we propose a test-time refinement pipeline that leverages implicit geometric constraints. We also introduce a novel Neural Feature Synthesizer (NeFeS) model, which encodes 3D geometric features during training and directly renders dense novel view features at test time to refine APR methods.
  arXiv  Detail & Related papers  (2023-03-17T16:10:50Z)
• Human Body Model Fitting by Learned Gradient Descent [48.79414884222403]
  We propose a novel algorithm for the fitting of 3D human shape to images. We show that this algorithm is fast (avg. 120ms convergence), robust to dataset, and achieves state-of-the-art results on public evaluation datasets.
  arXiv  Detail & Related papers  (2020-08-19T14:26:47Z)

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.