Papers with Code 아카이브
Cross-View Geo-Localisation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 6
- 보존된 평가 기록
- 25
Cross-view geo-localization refers to determining the geographic location of a camera or scene by matching images captured from different views, such as ground-level images (e.g., street-view or photos from handheld devices) and aerial/satellite images. This involves aligning and correlating these images despite significant variations in perspective, scale, and visual features.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
PEnG: Pose-Enhanced Geo-Localisation
CV-Cities: Advancing Cross-View Geo-Localization in Global Cities
SpaGBOL: Spatial-Graph-Based Orientated Localisation
BEV-CV: Birds-Eye-View Transform for Cross-View Geo-Localisation
Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation
VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval
Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching
The StreetLearn Environment and Dataset
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.