# SCD4VPR: Multi-modal Scene Change Detection for Long-term Visual Place Recognition Database Update

arXiv: https://arxiv.org/abs/2604.11402 · HTML: https://mlsanity.com/paper/2604.11402/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 25 of 25)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [MixVPR: Feature Mixing for Visual Place Recognition](https://mlsanity.com/paper/2303.02190/) (2023)
- [Optimal Transport Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2311.15937/) (2023)
- [MSeg: A Composite Dataset for Multi-domain Semantic Segmentation](https://mlsanity.com/paper/2112.13762/) (2021)
- [Weakly Supervised Silhouette-based Semantic Scene Change Detection](https://mlsanity.com/paper/1811.11985/) (2018)
- [ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments](https://mlsanity.com/paper/2103.05368/) (2021)
- [How to Reduce Change Detection to Semantic Segmentation](https://mlsanity.com/paper/2206.07557/) (2022)
- [Intelligent Reference Curation for Visual Place Recognition via Bayesian Selective Fusion](https://mlsanity.com/paper/2010.09228/) (2020)
- [SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-supervised Change Detector](https://mlsanity.com/paper/2405.04788/) (2024)
- [Towards Generalizable Scene Change Detection](https://mlsanity.com/paper/2409.06214/) (2024)
- [NYU-VPR: Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences](https://mlsanity.com/paper/2110.09004/) (2021)
- [Robust Scene Change Detection Using Visual Foundation Models and Cross-Attention Mechanisms](https://mlsanity.com/paper/2409.16850/) (2024)
- [CityPulse: Fine-Grained Assessment of Urban Change with Street View Time Series](https://mlsanity.com/paper/2401.01107/) (2024)
- [Epipolar-Guided Deep Object Matching for Scene Change Detection](https://mlsanity.com/paper/2007.15540/) (2020)
- [EMPLACE: Self-Supervised Urban Scene Change Detection](https://mlsanity.com/paper/2503.17716/) (2025)
- [StandardSim: A Synthetic Dataset For Retail Environments](https://mlsanity.com/paper/2202.02418/) (2022)
- [LT-Gaussian: Long-Term Map Update Using 3D Gaussian Splatting for Autonomous Driving](https://mlsanity.com/paper/2508.01704/) (2025)
- [UMAD: University of Macau Anomaly Detection Benchmark Dataset](https://mlsanity.com/paper/2408.12527/) (2024)
- [VGGT-MPR: VGGT-Enhanced Multimodal Place Recognition in Autonomous Driving Environments](https://mlsanity.com/paper/2602.19735/) (2026)
- [LaVPR: Benchmarking Language and Vision for Place Recognition](https://mlsanity.com/paper/2602.03253/) (2026)
- [Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images](https://mlsanity.com/paper/2504.08727/) (2025)

## Abstract (arXiv)

Long-term autonomy in mobile robotics requires maps that remain accurate as environments change over time. Visual Place Recognition (VPR), a core localization capability, degrades sharply as the temporal gap between query and database images grows, particularly across seasonal transitions. Scene Change Detection (SCD) offers a principled mechanism for database maintenance, but existing methods rely on binary, uni-modal visual features that cannot distinguish structural changes from viewpoint-induced differences - a distinction essential for correct update decisions. We propose SCD4VPR, a scene change detection that jointly reasons about what has changed and distinguishes genuine change from viewpoint-induced difference in a unified vision-language framework. SCD4VPR fuses VLM-generated semantic descriptions with visual features via cross-modal attention and refines predictions with geometric-semantic matching, producing multi-class change masks that separately identify object changes, appearance changes, and viewpoint-induced changes. We introduce NYC-CD, the first real-world street-view SCD benchmark with pixel-level multi-class annotations across 8,122 image pairs. Experiments across four SCD benchmarks show that SCD4VPR consistently improves three architecturally distinct backbones. In a controlled VPR database maintenance experiment on NYU-VPR spanning summer through late winter, we confirm that retrieval performance deteriorates substantially when the database is left unchanged, and show that SCD4VPR-guided updates recover most of this loss (+30.1 R@1 at the largest time gap) while keeping the database far more compact than naive append.