Alternatives and similar repositories for towards-generalizable-scene-change-detection

Users that are interested in towards-generalizable-scene-change-detection are comparing it to the libraries listed below

• kyusik-cho / ZSSCD
  Code for <Zero-Shot Scene Change Detection> in AAAI 2025
  ☆35Updated last week
• weihao1115 / mm-sam
  The official implementation of "Segment Anything with Multiple Modalities".
  ☆93Updated 9 months ago
• yejy53 / SG-BEV
  [CVPR 2024, Highlight] The official implementation of the paper "SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation…
  ☆38Updated 6 months ago
• ragavsachdeva / The-Change-You-Want-to-See
  The official implementation of the paper The Change You Want to See (WACV 2023).
  ☆62Updated last year
• chenshunpeng / FoL
  Official repository for the AAAI 2025 paper "Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition".
  ☆11Updated 3 weeks ago
• yejy53 / CVG-Text
  ☆13Updated 3 months ago
• vignywang / SAMFeat
  The official implementation of “Segment Anything Model is a Good Teacher for Local Feature Learning”.
  ☆114Updated 2 weeks ago
• bytedance / R2Former
  Official repository for R2Former: Unified Retrieval and Reranking Transformer for Place Recognition
  ☆92Updated 2 years ago
• ChadLin9596 / Robust-Scene-Change-Detection
  [ICRA-2025] Robust Scene Change Detection Using Visual Foundation Models and Cross-Attention Mechanisms
  ☆29Updated last month
• zyrant / SPGroup3D
  [AAAI 2024] SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection
  ☆41Updated last year
• AhmadArrabi / GPG2A
  Official implementation of the paper "Cross-View Meets Diffusion: Aerial Image Synthesis with Geometry and Text Guidance" (WACV 2025)
  ☆10Updated 3 months ago
• xsx1001 / AddressCLIP
  Official implementation and datasets of AddressCLIP
  ☆62Updated 11 months ago
• ga1i13o / Divide-and-Classify
  Official repository for ICCV23 paper "Divide&Classify: Fine-Grained Classification for City-Wide Visual Place Recognition"
  ☆19Updated last year
• feixue94 / matcha
  [CVPR 2025 Highlight] MATCHA: Towards Matching Anything.
  ☆60Updated last month
• Easonyesheng / A2PM-MESA
  [CVPR'24] MESA: Matching Everything by Segmenting Anything
  ☆140Updated 3 months ago
• DoongLi / Awesome-Scene-Change-Detection
  This repo contains a curative list of scene change detection(SCD), including papers, videos, codes, and related websites.
  ☆87Updated last week
• ragavsachdeva / CYWS-3D
  The official implementation of the paper The Change You Want to See (Now in 3D) (ICCVW 2023).
  ☆25Updated 11 months ago
• xlwangDev / HC-Net
  [NeurIPS 2023] Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator
  ☆65Updated last year
• YuHengsss / Trident
  [ICCV2025] Harnessing CLIP, DINO and SAM for Open Vocabulary Segmentation
  ☆58Updated this week
• Tong-Jin01 / EDTformer
  Visual Place Recognition
  ☆23Updated last month
• YujiaoShi / Boosting3DoFAccuracy
  ICCV2023: Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer
  ☆47Updated last year
• atfortes / ImageMatchingChallenge2022
  CVPR 2022 "Image Matching: Local Features and Beyond" workshop challenge: Silver Medal 🥈
  ☆23Updated 5 months ago
• sugar-fly / VSFormer
  [AAAI 2024] VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning
  ☆14Updated last year
• ml-research / deictic-segment-anything
  Segment Anything with Deictic Prompting
  ☆26Updated last month
• fanq15 / Stable-SAM
  ☆69Updated last year
• hmchuong / CoLLM
  [CVPR25] CoLLM: A Large Language Model for Composed Image Retrieval
  ☆25Updated 3 months ago
• BinuxLiu / NocPlace
  Nocturnal Visual Place Recognition via Generative and Inherited Knowledge Transfer
  ☆12Updated 6 months ago
• tudelft-iv / SliceMatch
  Cross-View Camera Pose Estimation [CVPR'23]
  ☆39Updated 3 months ago
• chenxi52 / CMPF
  Open-Vocabulary Panoptic Segmentation
  ☆24Updated last week
• yejy53 / EP-BEV
  [ECCV 2024] About The official implementation of the paper "Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network“.
  ☆83Updated last month