Visual Localization

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

5 leaderboard tables shown for this task, 5 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 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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

27 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 211 papers with code (402 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• SuperGlue: Learning Feature Matching with Graph Neural Networks
  26 Nov 2019 19 repositories listed Syntology ran 6 of 22 samples · 16 unverified · 6 pointer-only (licence)
  This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points.
• PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition
  10 Apr 2018 6 repositories listed
  This is largely due to the difficulty in extracting local feature descriptors from a point cloud that can subsequently be encoded into a global descriptor for the retrieval task.
• MegaLoc: One Retrieval to Place Them All
  24 Feb 2025 4 repositories listed Syntology ran 1 of 6 samples · 5 unverified
  We find that MegaLoc (1) achieves state of the art on a large number of Visual Place Recognition datasets, (2) impressive results on common Landmark Retrieval datasets, and (3) sets a new state of the art for Visual…
• BARF: Bundle-Adjusting Neural Radiance Fields
  13 Apr 2021 4 repositories listed Syntology ran 4 of 19 samples · 15 unverified
  In this paper, we propose Bundle-Adjusting Neural Radiance Fields (BARF) for training NeRF from imperfect (or even unknown) camera poses -- the joint problem of learning neural 3D representations and registering camera…
• LoFTR: Detector-Free Local Feature Matching with Transformers
  1 Apr 2021 4 repositories listed Syntology ran 14 of 16 samples · 2 unverified
  We present a novel method for local image feature matching.
• Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition
  2 Mar 2021 4 repositories listed Syntology ran 4 of 5 samples · 1 unverified
  Visual Place Recognition is a challenging task for robotics and autonomous systems, which must deal with the twin problems of appearance and viewpoint change in an always changing world.
• S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching
  3 Apr 2020 4 repositories listed
  Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms.
• Deep Closest Point: Learning Representations for Point Cloud Registration
  8 May 2019 4 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  To address local optima and other difficulties in the ICP pipeline, we propose a learning-based method, titled Deep Closest Point (DCP), inspired by recent techniques in computer vision and natural language processing.
• DSAC - Differentiable RANSAC for Camera Localization
  17 Nov 2016 4 repositories listed
  The 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.
• CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data
  16 Dec 2021 3 repositories listed Syntology ran 0 of 11 samples · 11 unverified
  We present a visual localization system that learns to estimate camera poses in the real world with the help of synthetic data.
• S2DNet: Learning Image Features for Accurate Sparse-to-Dense Matching
  1 Aug 2020 3 repositories listed
  Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms.
• AdaLAM: Revisiting Handcrafted Outlier Detection
  7 Jun 2020 3 repositories listed Syntology ran 0 of 19 samples · 19 unverified
  Local feature matching is a critical component of many computer vision pipelines, including among others Structure-from-Motion, SLAM, and Visual Localization.
• University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization
  27 Feb 2020 3 repositories listed Syntology ran 1 of 15 samples · 14 unverified
  To our knowledge, University-1652 is the first drone-based geo-localization dataset and enables two new tasks, i.
• Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses
  10 May 2019 3 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  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.
• From Coarse to Fine: Robust Hierarchical Localization at Large Scale
  9 Dec 2018 3 repositories listed Syntology ran 1 of 9 samples · 8 unverified · 2 pointer-only (licence)
  In this paper we propose HF-Net, a hierarchical localization approach based on a monolithic CNN that simultaneously predicts local features and global descriptors for accurate 6-DoF localization.
• Visual Localization Under Appearance Change: Filtering Approaches
  20 Nov 2018 3 repositories listed
  Our approaches rely on local features with an encoding technique to represent an image as a single vector.
• Neighbourhood Consensus Networks
  24 Oct 2018 3 repositories listed Syntology ran 5 of 21 samples · 16 unverified
  Second, we demonstrate that the model can be trained effectively from weak supervision in the form of matching and non-matching image pairs without the need for costly manual annotation of point to point correspondences.
• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
  24 Aug 2023 2 repositories listed Syntology ran 0 of 2 samples · 2 unverified · 2 pointer-only (licence)
  In this work, we introduce the Qwen-VL series, a set of large-scale vision-language models (LVLMs) designed to perceive and understand both texts and images.
• LightGlue: Local Feature Matching at Light Speed
  23 Jun 2023 2 repositories listed Syntology ran 18 of 40 samples · 22 unverified
  We introduce LightGlue, a deep neural network that learns to match local features across images.
• OrienterNet: Visual Localization in 2D Public Maps with Neural Matching
  4 Apr 2023 2 repositories listed
  We bridge this gap by introducing OrienterNet, the first deep neural network that can localize an image with sub-meter accuracy using the same 2D semantic maps that humans use.
• GlueStick: Robust Image Matching by Sticking Points and Lines Together
  4 Apr 2023 2 repositories listed Syntology ran 20 of 29 samples · 9 unverified · 15 pointer-only (licence)
  Line segments are powerful features complementary to points.
• HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion
  3 Apr 2023 2 repositories listed
  LiDAR relocalization plays a crucial role in many fields, including robotics, autonomous driving, and computer vision.
• PICCOLO: Point Cloud-Centric Omnidirectional Localization
  14 Aug 2021 2 repositories listed
  Our loss function, called sampling loss, is point cloud-centric, evaluated at the projected location of every point in the point cloud.
• Learning Multi-Scene Absolute Pose Regression with Transformers
  21 Mar 2021 2 repositories listed Syntology ran 10 of 20 samples · 10 unverified · 20 pointer-only (licence)
  Absolute camera pose regressors estimate the position and orientation of a camera from the captured image alone.
• Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs
  18 Jan 2021 2 repositories listed
  This mental model captures geometric and semantic aspects of the scene, describes the environment at multiple levels of abstractions (e.
• VR-Caps: A Virtual Environment for Capsule Endoscopy
  29 Aug 2020 2 repositories listed
  Current capsule endoscopes and next-generation robotic capsules for diagnosis and treatment of gastrointestinal diseases are complex cyber-physical platforms that must orchestrate complex software and hardware functions.
• Robust Image Retrieval-based Visual Localization using Kapture
  27 Jul 2020 2 repositories listed Syntology ran 0 of 5 samples · 5 unverified
  To demonstrate this, we present a versatile pipeline for visual localization that facilitates the use of different local and global features, 3D data (e.
• CMRNet++: Map and Camera Agnostic Monocular Visual Localization in LiDAR Maps
  20 Apr 2020 2 repositories listed
  In this paper, we now take it a step further by introducing CMRNet++, which is a significantly more robust model that not only generalizes to new places effectively, but is also independent of the camera parameters.
• Dynamic-SLAM: Semantic monocular visual localization and mapping based on deep learning in dynamic environment
  6 Jul 2019 2 repositories listed
  Then, in view of low recall rate of the existing SSD object detection network, a missed detection compensation algorithm based on the speed invariance in adjacent frames is proposed, which greatly improves the recall…
• Panoramic Annular Localizer: Tackling the Variation Challenges of Outdoor Localization Using Panoramic Annular Images and Active Deep Descriptors
  14 May 2019 2 repositories listed
  The 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.

Syntology lines on 17 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. Read from the graph 2026-09-24.