MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery
This work addresses a bottleneck in visual localization for robotics and computer vision, offering an incremental improvement over existing multi-scale methods.
The paper tackles the problem of generating richer place representations in Visual Place Recognition by augmenting NetVLAD with low-resolution image pyramid encoding, resulting in state-of-the-art Recall@N performance on 15 benchmarking datasets compared to 11 existing techniques.
Visual Place Recognition (VPR) is a crucial component of 6-DoF localization, visual SLAM and structure-from-motion pipelines, tasked to generate an initial list of place match hypotheses by matching global place descriptors. However, commonly-used CNN-based methods either process multiple image resolutions after training or use a single resolution and limit multi-scale feature extraction to the last convolutional layer during training. In this paper, we augment NetVLAD representation learning with low-resolution image pyramid encoding which leads to richer place representations. The resultant multi-resolution feature pyramid can be conveniently aggregated through VLAD into a single compact representation, avoiding the need for concatenation or summation of multiple patches in recent multi-scale approaches. Furthermore, we show that the underlying learnt feature tensor can be combined with existing multi-scale approaches to improve their baseline performance. Evaluation on 15 viewpoint-varying and viewpoint-consistent benchmarking datasets confirm that the proposed MultiRes-NetVLAD leads to state-of-the-art Recall@N performance for global descriptor based retrieval, compared against 11 existing techniques. Source code is publicly available at https://github.com/Ahmedest61/MultiRes-NetVLAD.