pith. sign in

arxiv: 2412.08376 · v2 · pith:OCLCP73Pnew · submitted 2024-12-11 · 💻 cs.CV

Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization

Siyan Dong , Shuzhe Wang , Shaohui Liu , Lulu Cai , Qingnan Fan , Juho Kannala , Yanchao Yang This is my paper
classification 💻 cs.CV
keywords posecamerareloc3rlocalizationrelativevisualaccurateestimates
0
0 comments X
read the original abstract

Visual localization aims to determine the camera pose of a query image relative to a database of posed images. In recent years, deep neural networks that directly regress camera poses have gained popularity due to their fast inference capabilities. However, existing methods struggle to either generalize well to new scenes or provide accurate camera pose estimates. To address these issues, we present Reloc3r, a simple yet effective visual localization framework. It consists of an elegantly designed relative pose regression network, and a minimalist motion averaging module for absolute pose estimation. Trained on approximately eight million posed image pairs, Reloc3r achieves surprisingly good performance and generalization ability. We conduct extensive experiments on six public datasets, consistently demonstrating the effectiveness and efficiency of the proposed method. It provides high-quality camera pose estimates in real time and generalizes to novel scenes. Code: https://github.com/ffrivera0/reloc3r.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training

    cs.CV 2026-07 unverdicted novelty 7.0

    GeoMix achieves new state-of-the-art results in descriptor-free 2D-3D matching by adding directional embeddings, learnable global context nodes, and multi-detector training, cutting rotation and translation errors by ...

  2. CasaMaestro: Multi-View Panoramas for House-Scale 3D Reconstruction

    cs.CV 2026-06 unverdicted novelty 7.0

    CasaMaestro predicts metric depth and poses from sparse multi-view panoramas to enable fast house-scale 3D reconstruction.

  3. 3DReflecNet: A Large-Scale Dataset for 3D Reconstruction of Reflective, Transparent, and Low-Texture Objects

    cs.CV 2026-05 unverdicted novelty 7.0

    3DReflecNet is a 22 TB+ dataset of over 120,000 synthetic and 1,000 real objects with millions of multi-view frames for benchmarking 3D reconstruction on reflective, transparent, and low-texture surfaces.

  4. A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features

    cs.CV 2025-10 unverdicted novelty 7.0

    FastForward represents scenes as collections of 3D-anchored image features and performs camera pose estimation via feed-forward correspondence prediction, achieving competitive accuracy with minimal mapping time.

  5. VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

    cs.CV 2025-05 unverdicted novelty 7.0

    VGGT-SLAM aligns VGGT submaps via SL(4) manifold optimization of 15-DoF homographies to enable consistent dense RGB SLAM on long uncalibrated monocular videos.

  6. Privacy-Preserving Structureless Visual Localization via Image Obfuscation

    cs.CV 2026-04 unverdicted novelty 6.0

    Simple image obfuscation enables privacy-preserving structureless visual localization with standard feature matchers and no pipeline changes, achieving state-of-the-art accuracy among privacy methods.

  7. TTT3R: 3D Reconstruction as Test-Time Training

    cs.CV 2025-09 unverdicted novelty 5.0

    TTT3R derives a closed-form learning rate from memory-observation alignment confidence to boost length generalization in RNN-based 3D reconstruction by 2x in global pose estimation.