paper-with-me

Visual Localization

5개 벤치마크 · 논문 494편 · 이 태스크의 논문 보기 →

Benchmarks

Oxford RobotCar Full

결과 6개

Extended CMU Seasons

결과 1개

RobotCar Seasons v2

결과 1개

Most implemented

MegaLoc: One Retrieval to Place Them All

2025-02-24 · 구현 4개

Papers

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

전체 494편 보기 →