CVDec 8, 2018

Semantically-Aware Attentive Neural Embeddings for Image-based Visual Localization

arXiv:1812.03402v210 citations
Originality Incremental advance
AI Analysis

This addresses robust localization in dynamic environments for applications like robotics or augmented reality, with incremental improvements in performance.

The paper tackles image-based visual localization by combining appearance and semantic information to handle large perceptual changes and time lags, reporting an average 19% improvement over state-of-the-art methods.

We present an approach that combines appearance and semantic information for 2D image-based localization (2D-VL) across large perceptual changes and time lags. Compared to appearance features, the semantic layout of a scene is generally more invariant to appearance variations. We use this intuition and propose a novel end-to-end deep attention-based framework that utilizes multimodal cues to generate robust embeddings for 2D-VL. The proposed attention module predicts a shared channel attention and modality-specific spatial attentions to guide the embeddings to focus on more reliable image regions. We evaluate our model against state-of-the-art (SOTA) methods on three challenging localization datasets. We report an average (absolute) improvement of $19\%$ over current SOTA for 2D-VL. Furthermore, we present an extensive study demonstrating the contribution of each component of our model, showing $8$--$15\%$ and $4\%$ improvement from adding semantic information and our proposed attention module. We finally show the predicted attention maps to offer useful insights into our model.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes