Browse State-of-the-Art › Camera Localization
Camera Localization
52 papers with code · 2 benchmarks · 9 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 2 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Aachen Day-Night benchmark (2 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Oxford RobotCar Full (6 rows) | RobustLoc | RobustLoc: Robust Camera Pose Regression in Challenging Driving... | code | — | Compare |
| Aachen Day-Night benchmark (2 rows) | PoSFeat | Decoupling Makes Weakly Supervised Local Feature Better | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
9 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
2 subtasks in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 116 · with a code link: 52 · where Syntology ran a sample: 6 (6 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (6 of 116 tagged: 6 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 116, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
17 Nov 2016 4 repositories listedThe most promising approach is inspired by reinforcement learning, namely to replace the deterministic hypothesis selection by a probabilistic selection for which we can derive the expected loss w. r. t.
-
10 May 2019 3 repositories listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples)In contrast, we learn hypothesis search in a principled fashion that lets us optimize an arbitrary task loss during training, leading to large improvements on classic computer vision tasks.
-
4 Dec 2022 2 repositories listedThe proposed approach uses sparse descriptors to regress the scene coordinates, instead of a dense RGB image.
-
16 Mar 2021 2 repositories listed Syntology community repositories only · 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples) · 10 pointer-only (licence)In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms.
-
9 Apr 2020 2 repositories listedWe present a multimodal camera relocalization framework that captures ambiguities and uncertainties with continuous mixture models defined on the manifold of camera poses.
-
1 Dec 2019 2 repositories listedWe thus propose to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness.
-
24 Jun 2019 2 repositories listedIn this paper we present CMRNet, a realtime approach based on a Convolutional Neural Network to localize an RGB image of a scene in a map built from LiDAR data.
-
14 May 2019 2 repositories listedThe panoramic annular images captured by the single camera are processed and fed into the NetVLAD network to form the active deep descriptor, and sequential matching is utilized to generate the localization result.
-
7 Oct 2015 2 repositories listedEvent-based vision sensors mimic the operation of biological retina and they represent a major paradigm shift from traditional cameras.
-
28 Dec 2024 1 repository listedWe present GSplatLoc, a camera localization method that leverages the differentiable rendering capabilities of 3D Gaussian splatting for ultra-precise pose estimation.
-
24 Nov 2024 1 repository listedTo solve this limitation, we propose combining cross-view geo-localisation and relative pose estimation to increase precision to a level practical for real-world application.
-
13 Nov 2024 1 repository listedIn our experiments, we demonstrate that MBA-SLAM surpasses previous state-of-the-art methods in both camera localization and map reconstruction, showcasing superior performance across a range of datasets, including…
-
12 Oct 2024 1 repository listedVisual correspondence is a crucial step in key computer vision tasks, including camera localization, image registration, and structure from motion.
-
23 Sep 2024 1 repository listedSpaGBOL achieves state-of-the-art accuracies on the unseen test graph - with relative Top-1 retrieval improvements on previous techniques of 11%, and 50% when filtering with Bearing Vector Matching on the SpaGBOL…
-
18 Sep 2024 1 repository listedRe-identification (ReID) is a critical challenge in computer vision, predominantly studied in the context of pedestrians and vehicles.
-
10 Sep 2024 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)To alleviate this issue, this paper proposes a weakly supervised learning strategy for ground-to-satellite image registration when only noisy pose labels for ground images are available for network training.
-
16 Apr 2024 1 repository listedIn this paper, we present SPVLoc, a global indoor localization method that accurately determines the six-dimensional (6D) camera pose of a query image and requires minimal scene-specific prior knowledge and no…
-
31 Jan 2024 1 repository listedTo mitigate the capacity issue, we propose to split the landmarks into subgroups and train a separate network for each subgroup.
-
23 Jan 2024 1 repository listedThis approach enables the creation of a semantic map of the environment and ensures reliable camera localization.
-
23 Dec 2023 1 repository listedCross-view image matching for geo-localisation is a challenging problem due to the significant visual difference between aerial and ground-level viewpoints.
-
16 Sep 2023 1 repository listedTo address this challenge, we propose Dynamic Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fields (DynaMoN).
-
16 Jul 2023 1 repository listedIn this paper, we propose a method to increase the accuracy of a ground camera's location and orientation by estimating the relative rotation and translation between the ground-level image and its matched/retrieved…
-
29 May 2023 1 repository listedOur results also suggest that when a large localization dataset with high quality is available, training from scratch leads to better performances.
-
1 May 2023 1 repository listedThe proposed approach maps image features from different camera views of the same 3D region to nearby points in the learned feature space.
-
19 Dec 2022 1 repository listedWe tackle a new problem of multi-view camera and subject registration in the bird's eye view (BEV) without pre-given camera calibration.
-
14 Dec 2022 1 repository listedSparse local feature extraction is usually believed to be of important significance in typical vision tasks such as simultaneous localization and mapping, image matching and 3D reconstruction.
-
21 Nov 2022 1 repository listed Syntology 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)We present ESLAM, an efficient implicit neural representation method for Simultaneous Localization and Mapping (SLAM).
-
21 Nov 2022 1 repository listedState-of-the-art feature matching methods require each scene to be stored as a 3D point cloud with per-point features, consuming several gigabytes of storage per scene.
-
21 Nov 2022 1 repository listedExperiments demonstrate that RobustLoc surpasses current state-of-the-art camera pose regression models and achieves robust performance in various environments.
-
22 Oct 2022 1 repository listedWe perform localisation by aligning room layout inferred from a panorama image with the floor plan of a scene.
-
13 Jul 2022 1 repository listed
-
10 Apr 2022 1 repository listed
-
8 Jan 2022 1 repository listed
-
1 Jan 2022 1 repository listed
-
1 Jan 2022 1 repository listed
-
20 Aug 2021 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)
-
19 Apr 2021 1 repository listed
-
31 Mar 2021 1 repository listed
-
8 Dec 2020 1 repository listed
-
1 Apr 2020 1 repository listed
-
18 Mar 2020 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples)
-
12 Mar 2020 1 repository listed
-
22 Nov 2019 1 repository listed
-
1 Oct 2019 1 repository listed
-
8 Sep 2019 1 repository listed
-
7 Aug 2019 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
18 Feb 2019 1 repository listed
-
20 Feb 2018 1 repository listed
-
9 Dec 2017 1 repository listed
-
28 Nov 2017 1 repository listed
-
12 Oct 2016 1 repository listed
-
1 Jun 2016 1 repository listed
-
4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians28 May 2025 0 repositories listed
-
NeuroLoc: Encoding Navigation Cells for 6-DOF Camera Localization2 May 2025 0 repositories listed
-
HAL-NeRF: High Accuracy Localization Leveraging Neural Radiance Fields11 Apr 2025 0 repositories listed
-
3D Densification for Multi-Map Monocular VSLAM in Endoscopy18 Mar 2025 0 repositories listed
-
IM360: Textured Mesh Reconstruction for Large-scale Indoor Mapping with 360° Cameras18 Feb 2025 0 repositories listed
-
PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environments24 Nov 2024 0 repositories listed
-
Monocular Visual Place Recognition in LiDAR Maps via Cross-Modal State Space Model and Multi-View Matching8 Oct 2024 0 repositories listed
-
EgoHDM: An Online Egocentric-Inertial Human Motion Capture, Localization, and Dense Mapping System31 Aug 2024 0 repositories listed
-
CMR-Agent: Learning a Cross-Modal Agent for Iterative Image-to-Point Cloud Registration5 Aug 2024 0 repositories listed
-
360 in the Wild: Dataset for Depth Prediction and View Synthesis27 Jun 2024 0 repositories listed
-
View-Invariant Pixelwise Anomaly Detection in Multi-object Scenes with Adaptive View Synthesis26 Jun 2024 0 repositories listed
-
High-fidelity Endoscopic Image Synthesis by Utilizing Depth-guided Neural Surfaces20 Apr 2024 0 repositories listed
-
Learning Neural Volumetric Pose Features for Camera Localization19 Mar 2024 0 repositories listed
-
Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds1 Jan 2024 0 repositories listed
-
Residual Learning for Image Point Descriptors24 Dec 2023 0 repositories listed
-
CaLDiff: Camera Localization in NeRF via Pose Diffusion23 Dec 2023 0 repositories listed
-
3DS-SLAM: A 3D Object Detection based Semantic SLAM towards Dynamic Indoor Environments10 Oct 2023 0 repositories listed
-
Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization27 Sep 2023 0 repositories listed
-
PAg-NeRF: Towards fast and efficient end-to-end panoptic 3D representations for agricultural robotics11 Sep 2023 0 repositories listed
-
SGL: Structure Guidance Learning for Camera Localization12 Apr 2023 0 repositories listed
-
Visual Perception System for Autonomous Driving3 Mar 2023 0 repositories listed
-
Attention-Enhanced Cross-modal Localization Between 360 Images and Point Clouds6 Dec 2022 0 repositories listed
-
A Faster, Lighter and Stronger Deep Learning-Based Approach for Place Recognition27 Nov 2022 0 repositories listed
-
Uncertainty-Aware DNN for Multi-Modal Camera Localization2 Nov 2022 0 repositories listed
-
CVLNet: Cross-View Semantic Correspondence Learning for Video-based Camera Localization7 Aug 2022 0 repositories listed
-
Deep Camera Pose Regression Using Pseudo-LiDAR28 Feb 2022 0 repositories listed
-
A Critical Analysis of Image-based Camera Pose Estimation Techniques15 Jan 2022 0 repositories listed
-
NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning23 Dec 2021 0 repositories listed
-
RADA: Robust Adversarial Data Augmentation for Camera Localization in Challenging Weather5 Dec 2021 0 repositories listed
-
S3LAM: Structured Scene SLAM15 Sep 2021 0 repositories listed
-
Monocular Camera Localization for Automated Vehicles Using Image Retrieval13 Sep 2021 0 repositories listed
-
DistillPose: Lightweight Camera Localization Using Auxiliary Learning9 Aug 2021 0 repositories listed
-
Uncertainty-Aware Camera Pose Estimation from Points and Lines8 Jul 2021 0 repositories listed
-
Video-Based Camera Localization Using Anchor View Detection and Recursive 3D Reconstruction7 Jul 2021 0 repositories listed
-
Deep auxiliary learning for visual localization using colorization task1 Jul 2021 0 repositories listed
-
End-to-end learning of keypoint detection and matching for relative pose estimation2 Apr 2021 0 repositories listed
-
19 Mar 2021 0 repositories listed
-
Motion-based Camera Localization System in Colonoscopy Videos3 Dec 2020 0 repositories listed
-
Co-Attention for Conditioned Image Matching16 Jul 2020 0 repositories listed
-
PoseGAN: A Pose-to-Image Translation Framework for Camera Localization23 Jun 2020 0 repositories listed
-
1 Jun 2020 0 repositories listed
-
3D Scene Geometry-Aware Constraint for Camera Localization with Deep Learning13 May 2020 0 repositories listed
-
Monocular Direct Sparse Localization in a Prior 3D Surfel Map23 Feb 2020 0 repositories listed
-
ViPR: Visual-Odometry-aided Pose Regression for 6DoF Camera Localization17 Dec 2019 0 repositories listed
-
A Robust Stereo Camera Localization Method with Prior LiDAR Map Constrains2 Dec 2019 0 repositories listed
-
Line-based Camera Pose Estimation in Point Cloud of Structured Environments23 Nov 2019 0 repositories listed
-
Privacy Preserving Image Queries for Camera Localization1 Oct 2019 0 repositories listed
-
SANet: Scene Agnostic Network for Camera Localization1 Oct 2019 0 repositories listed
Syntology lines on 7 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections