Environmental Change Detection: Toward a Practical Task of Scene Change Detection

TL;DR

This paper introduces Environmental Change Detection (ECD), a practical scene change detection task that relies on environmental cues from uncurated images, addressing limitations of traditional methods that require aligned reference images.

Contribution

It proposes a novel framework for ECD that leverages multiple reference candidates and semantic aggregation, advancing scene change detection in real-world, unaligned settings.

Findings

Outperforms naive combinations of state-of-the-art methods on ECD benchmarks.

Achieves performance comparable to the oracle setting with ideal reference alignment.

Provides a large-scale uncurated image database for practical ECD evaluation.

Abstract

Humans do not memorize everything. Thus, humans recognize scene changes by exploring the past images. However, available past (i.e., reference) images typically represent nearby viewpoints of the present (i.e., query) scene, rather than the identical view. Despite this practical limitation, conventional Scene Change Detection (SCD) has been formalized under an idealized setting in which reference images with matching viewpoints are available for every query. In this paper, we push this problem toward a practical task and introduce Environmental Change Detection (ECD). A key aspect of ECD is to avoid unrealistically aligned query-reference pairs and rely solely on environmental cues. Inspired by real-world practices, we provide these cues through a large-scale database of uncurated images. To address this new task, we propose a novel framework that jointly understands spatial environments and detects changes. The main idea is that matching at the same spatial locations between a query and a reference may lead to a suboptimal solution due to viewpoint misalignment and limited field-of-view (FOV) coverage. We deal with this limitation by leveraging multiple reference candidates and aggregating semantically rich representations for change detection. We evaluate our framework on three standard benchmark sets reconstructed for ECD, and significantly outperform a naive combination of state-of-the-art methods while achieving comparable performance to the oracle setting. The code will be released upon acceptance.