paper-with-me

Papers Visual Localization

“Visual Localization” 태그가 달린 논문 494편 · 필터 해제

SSMB: Self-Supervised Local Feature Detection under Motion Blur

2026-08-27 · Zhenjun Zhao, Fabio Bellavia, Wenting Wang, Fan Zhu 외 arxiv

Keypoint detection under motion blur remains a significant challenge, as blur distorts local image structure and degrades the repeatability of feature localization. Existing approaches either rely on computationally expe…

Visual LocalizationKeypoint DetectionPose EstimationImage Matching

Spotter: Efficient Urban Visual Localization via Geo-Referenced Facade Landmarks in GPS-Degraded Environments

2026-08-24 · Antoni Valls, Jordi Sanchez-Riera arxiv

Accurate visual localization on robotic and wearable platforms remains challenging in dense urban environments. Existing methodologies typically rely on GPS for absolute positioning, yet GPS signals frequently degrade in…

Visual LocalizationCamera LocalizationVisual Odometry

Misanthrope: A Privacy-Preserving Keypoint Detector

2026-08-24 · Francesco Vultaggio, Predrag Djindjic, Markus Gerke, Sebastian Tschiatschek 외 arxiv

Image matching is a core component of applications such as Simultaneous Localization and Mapping (SLAM), Visual Localization, and Structure from Motion (SfM). However, the local image features central to this task are vu…

Visual LocalizationImage Matching

DRAgent: Discriminative Reasoning Agent for Referring Expression Segmentation

2026-08-24 · Yujie Qi, Luyan Zhang arxiv

Referring Expression Segmentation (RES) aims to generate a pixel-level mask for the object specified by a language expression. Recent methods based on multimodal large language models (MLLMs) often rely on one-pass coord…

Referring Expression SegmentationVisual Localization

Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ

2026-08-13 · Zongyun Zhang, Jiacheng Ruan, Xian Gao, Ruizhu Zhou 외 arxiv

Although multimodal large language models (MLLMs) have shown substantial potential in visual understanding and graphic code generation, editing scientific figures through code presents a greater challenge: a model must j…

Instruction FollowingVisual LocalizationCode Generation

GS-CPE: Unified 6-Degree-of-Freedom Camera Pose Estimation via 3D Gaussian Splatting

2026-08-11 · Huaiyuan Weng, Chul Min Yeum, Su-Min Kang arxiv

Despite substantial progress in visual localization, from scene coordinate regression to direct camera pose regression, achieving both robust generalization and high accuracy remain challenging. This study introduces GS-…

Camera Pose EstimationVisual Localization

Topometric Autonomous Vehicle Localization by Combining Visual Embeddings and Feed-Forward 3D Models

2026-08-06 · Eulogio Quemada-Torres, Alberto Jaenal, Francisco-Angel Moreno, Javier Gonzalez-Jimenez arxiv

Effective Visual Localization (VL) requires a map of the environment that combines compactness for efficient scalability with robustness against visual appearance changes and metric precision. Through low-dimensional ima…

Visual Place RecognitionVisual LocalizationPose Estimation

SGFormer: Structure-Guided Transformer for Robust Local Feature Matching

2026-08-04 · Runyu Zhu arxiv

Local feature matching is a fundamental component of photogrammetry, enabling accurate image correspondence critical for tasks such as 3D reconstruction, stereo mapping, and visual localization. While recent detector-fre…

Visual Localization3D Reconstruction

RIM: A Retrieval-In-Matching Framework for Cross-Domain Global Visual Localization of UAVs

2026-07-22 · Xin Li, Siyuan Duan, Shang Wang, Zhimin Mao 외 arxiv

Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention. However, acquisition-time and imaging-platform differences between UAV and reference i…

Visual LocalizationPose Estimation

SceneBind: Binding What and Where Across Vision, Audio and Language

2026-07-16 · Mingfei Chen, Zijun Cui, Ruoke Zhang, Hyeonggon Ryu 외 arxiv

We present SceneBind, an omni-modal representation of realistic scenes with joint semantic and 3D spatial understanding across vision, audio and language. Existing omni-modal encoders excel at instance-level semantics (i…

Visual Localization

VTAP Gripper: Synergizing Fingertip Sensing and a Visuo-Tactile Active Palm for Dexterous In-Hand Manipulation

2026-07-16 · Yuhao Zhou, Sheeraz Athar, Zhixian Hu, Binghao Huang 외 arxiv

This paper presents a tactile-reactive gripper that integrates a Visuo-Tactile Active Palm (VTAP) and compliant, reconfigurable fingers equipped with tactile array sensors. The design exploits structured finger-palm syne…

Visual Localization

Reference-Induced Consensus for Selective Posed-Reference Visual Localization

2026-07-06 · Wonseok Kang, Jaehyun Kim, Jeongmin Lee, Tae-Wan Kim arxiv

We present RIC-Loc (Reference-Induced Consensus localization), a scene-training-free posed-reference localizer that is SfM-point-map-free in its main estimator: it uses known reference poses, but not precomputed SfM 3D m…

Visual Localization

DIVO: Continuous-time DVL-Inertial-Visual Odometry for Unmanned Underwater Vehicles

2026-07-06 · Kyungmin Jung, Angad Bajwa, Junha Yoo, Arturo Del Castillo Bernal 외 arxiv

This paper presents a novel acoustic-visual-inertial odometry solution leveraging a continuous-time trajectory estimation framework for unmanned underwater vehicles. Underwater environments present unique challenges for …

Visual LocalizationGaussian ProcessesVisual TrackingVisual Odometry

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

2026-07-02 · Yejun Zhang, Xinjue Wang, Zihan Wang, Esa Rahtu 외 arxiv

Descriptor-free visual localization eliminates high-dimensional descriptor storage, preserves scene privacy, and simplifies map maintenance, yet its accuracy still lags far behind descriptor-based pipelines. We identify …

Visual Localization

AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images

2026-06-30 · Meng Yang, Zizhuo Li, Linfeng Tang, Fan Fan 외 arxiv

Multi-modal image matching is essential for visual localization and multi-sensor fusion, but it is hindered by the scarcity of large-scale training data with precise geometric annotations. Existing real-world datasets su…

Monocular Depth EstimationVisual LocalizationImage Matching

Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression

2026-06-30 · Oleksii Nasypanyi, Jaemin Cho, Utku Ozbulak, Byungkon Kang 외 arxiv

Scene Coordinate Regression (SCR) methods are increasingly adopted for visual localization. In these approaches, the scene is implicitly encoded within a neural network that regresses a 3D world coordinate for each image…

Visual Localization

From Open Waters to Enclosed Cabins: ProteusVPR for Cross-Scene Visual Place Recognition in Maritime Perception and Cabin Inspection

2026-06-23 · Zexi Chen, Zitai Huang, Qiwen Gu, Zhiqi Li 외 arxiv

Autonomous robotic inspection in maritime environments presents unique challenges for Visual Place Recognition (VPR) due to cross-scene perceptual shifts. Robots navigating ship-borne environments must transition between…

Visual Place RecognitionVisual LocalizationImage Retrieval

SG2Loc: Sequential Visual Localization on 3D Scene Graphs

2026-06-10 · Nicole Damblon, Olga Vysotska, Federico Tombari, Marc Pollefeys 외 arxiv

Visual localization in complex indoor environments remains a critical challenge for robotics and AR applications. Sequential localization, where pose estimates are refined over time, is important for autonomous agents. H…

Visual LocalizationPoint Clouds

Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives

2026-06-03 · Ayumi Umemura, Toshinori Kuwahara, Marc Pollefeys, Daniel Barath arxiv

Visual localization -- estimating a camera pose within a pre-existing map -- is a fundamental problem in computer vision. Floorplans are an attractive map representation: they are readily available for most buildings, co…

Visual Localization

SAMatcher: Co-Visibility Modeling with Segment Anything for Robust Feature Matching

2026-06-02 · Xu Pan, Qiyuan Ma, Mingyue Dong, He Chen 외 arxiv

Reliable correspondence estimation is a fundamental problem in image processing, underpinning applications such as Structure from Motion, visual localization, and image registration. Existing learning-based methods have …

Representation LearningVisual LocalizationImage RegistrationImage Matching
1–20 / 494 다음 →