SOTAVerified

Visual Place Recognition

Visual Place Recognition is the task of matching a view of a place with a different view of the same place taken at a different time.

Source: Visual place recognition using landmark distribution descriptors

Image credit: Visual place recognition using landmark distribution descriptors

Papers

Showing 1–10 of 297 papers

TitleStatusHype
Visual Place Recognition for Large-Scale UAV Applications—0
Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition—0
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot NavigationCode1
Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning—0
HypeVPR: Exploring Hyperbolic Space for Perspective to Equirectangular Visual Place RecognitionCode0
TAT-VPR: Ternary Adaptive Transformer for Dynamic and Efficient Visual Place Recognition—0
Place Recognition: A Comprehensive Review, Current Challenges and Future DirectionsCode2
MMS-VPR: Multimodal Street-Level Visual Place Recognition Dataset and Benchmark—0
Geolocating Earth Imagery from ISS: Integrating Machine Learning with Astronaut Photography for Enhanced Geographic MappingCode0
Visual Re-Ranking with Non-Visual Side InformationCode0
Show:102550
← PrevPage 1 of 30Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SegVLAD-PreT (M)Recall@167.2—Unverified
2AnyLoc-VLAD-DINOv2Recall@166.74—Unverified
3DINOv2Recall@145.23—Unverified
4CLIPRecall@136.59—Unverified
5DINORecall@124.02—Unverified
6MixVPRRecall@110.31—Unverified
7CosPlaceRecall@18.12—Unverified
8NetVLADRecall@16.39—Unverified