Visual Localization
5개 벤치마크 · 논문 494편 · 이 태스크의 논문 보기 →
Benchmarks
Most implemented
SuperGlue: Learning Feature Matching with Graph Neural Networks
MegaLoc: One Retrieval to Place Them All
BARF: Bundle-Adjusting Neural Radiance Fields
LoFTR: Detector-Free Local Feature Matching with Transformers
Papers
SSMB: Self-Supervised Local Feature Detection under Motion Blur
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 MatchingSpotter: Efficient Urban Visual Localization via Geo-Referenced Facade Landmarks in GPS-Degraded Environments
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 OdometryMisanthrope: A Privacy-Preserving Keypoint Detector
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 MatchingDRAgent: Discriminative Reasoning Agent for Referring Expression Segmentation
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 LocalizationEdit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ
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 GenerationGS-CPE: Unified 6-Degree-of-Freedom Camera Pose Estimation via 3D Gaussian Splatting
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