Densernet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation

Abstract

In this work, we introduce a Denser Feature Network (DenserNet) for visual localization. Our work provides three principal contributions. First, we develop a convolutional neural network (CNN) architecture which aggregates feature maps at different semantic levels for image representations. Using denser feature maps, our method can produce more keypoint features and increase image retrieval accuracy. Second, our model is trained end-to-end without pixel-level annotation other than positive and negative GPS-tagged image pairs. We use a weakly supervised triplet ranking loss to learn discriminative features and encourage keypoint feature repeatability for image representation. Finally, our method is computationally efficient as our architecture has shared features and parameters during computation. Our method can perform accurate large-scale localization under challenging conditions while remaining the computational constraint. Extensive experiment results indicate that our method sets a

Stats

• citations120
• S2 citations—
• github stars0
• HF likes0
• heat score15.62
• arxiv keyliu2020densernet

Related papers

• Yes, We CANN: Constrained Approximate Nearest Neighbors For Local Feature-based Visual Localization (2023)14.99
• Sparse-to-dense Hypercolumn Matching For Long-term Visual Localization (2019)12.99
• Leveraging Efficientnet And Contrastive Learning For Accurate Global-scale Location Estimation (2021)9.03
• Reuse Your Features: Unifying Retrieval And Feature-metric Alignment (2022)1.69
• Multires-netvlad: Augmenting Place Recognition Training With Low-resolution Imagery (2022)16.01
• Logg3d-net: Locally Guided Global Descriptor Learning For 3D Place Recognition (2021)19.02
• Supergf: Unifying Local And Global Features For Visual Localization (2022)0.00
• DH3D: Deep Hierarchical 3D Descriptors For Robust Large-scale 6dof Relocalization (2020)14.76