https://github.com/Jeff-Zilence/VIGOR
공식 코드VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Skyy93/Sample4Geo
공식 코드Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation
https://github.com/cav-research-lab/geovlm
공식 코드GeoVLM: Improving Automated Vehicle Geolocalisation Using Vision-Language Matching
https://github.com/deepmind/streetlearn
공식 코드https://github.com/gaoshuang98/cvcities
공식 코드CV-Cities: Advancing Cross-View Geo-Localization in Global Cities
https://github.com/shiyujiao/cross_view_localization_DSM
공식 코드Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching
https://github.com/tavisshore/BEV-CV
공식 코드BEV-CV: Birds-Eye-View Transform for Cross-View Geo-Localisation
https://github.com/tavisshore/PEnG
공식 코드https://github.com/tavisshore/SpaGBOL
공식 코드https://github.com/google-deepmind/streetlearn
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.